Tootfinder

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horvath, Martin Takac, Eduard Gorbunov
https://arxiv.org/abs/2403.02648

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Adaptive methods are extremely popular in machine learning as they make learning rate tuning less expensive. This paper introduces a novel optimization algorithm named KATE, which presents a scale-invariant adaptation of the well-known AdaGrad algorithm. We prove the scale-invariance of KATE for the case of Generalized Linear Models. Moreover, for general smooth non-convex problems, we establish a convergence rate of $O \left(\frac{\log T}{\sqrt{T}} \right)$ for KATE, matching the best-known on…

This https://arxiv.org/abs/2402.14961 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Reinforcement Learning with Elastic Time Steps
Traditional Reinforcement Learning (RL) algorithms are usually applied in robotics to learn controllers that act with a fixed control rate. Given the discrete nature of RL algorithms, they are oblivious to the effects of the choice of control rate: finding the correct control rate can be difficult and mistakes often result in excessive use of computing resources or even lack of convergence. We propose Soft Elastic Actor-Critic (SEAC), a novel off-policy actor-critic algorithm to address this is…

Model-based Deep Learning for Rate Split Multiple Access in Vehicular Communications
Hanwen Zhang, Mingzhe Chen, Alireza Vahid, Haijian Sun
https://arxiv.org/abs/2405.01515

Model-based Deep Learning for Rate Split Multiple Access in Vehicular Communications
Rate split multiple access (RSMA) has been proven as an effective communication scheme for 5G and beyond, especially in vehicular scenarios. However, RSMA requires complicated iterative algorithms for proper resource allocation, which cannot fulfill the stringent latency requirement in resource constrained vehicles. Although data driven approaches can alleviate this issue, they suffer from poor generalizability and scarce training data. In this paper, we propose a fractional programming (FP) ba…

This https://arxiv.org/abs/2402.19276 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze the video content in its aggressively downsampled format, while being blind to the impact of actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model, and a method of training it to improve its modularity. Spec…

Heart Rate and Body Temperature Relationship in Children Admitted to PICU -- A Machine Learning Approach
Emilie Lu, Thanh-Dung Le
https://arxiv.org/abs/2405.00180

Heart Rate and Body Temperature Relationship in Children Admitted to PICU -- A Machine Learning Approach
Vital signs have been essential clinical measures. Among these, body temperature (BT) and heart rate (HR) are particularly significant, and numerous studies explored their association in hospitalized adults and children. However, a lack of in-depth research persists in children admitted to the pediatric intensive care unit (PICU) despite their critical condition requiring particular attention. Objective: In this study, we explore the relationship between HR and BT in children from 0 to 18 years…

Masks, Signs, And Learning Rate Rewinding
Advait Gadhikar, Rebekka Burkholz
https://arxiv.org/abs/2402.19262 https://arxiv.org/pdf/24…

Masks, Signs, And Learning Rate Rewinding
Learning Rate Rewinding (LRR) has been established as a strong variant of Iterative Magnitude Pruning (IMP) to find lottery tickets in deep overparameterized neural networks. While both iterative pruning schemes couple structure and parameter learning, understanding how LRR excels in both aspects can bring us closer to the design of more flexible deep learning algorithms that can optimize diverse sets of sparse architectures. To this end, we conduct experiments that disentangle the effect of ma…

This https://arxiv.org/abs/2402.14961 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Reinforcement Learning with Elastic Time Steps
Traditional Reinforcement Learning (RL) algorithms are usually applied in robotics to learn controllers that act with a fixed control rate. Given the discrete nature of RL algorithms, they are oblivious to the effects of the choice of control rate: finding the correct control rate can be difficult and mistakes often result in excessive use of computing resources or even lack of convergence. We propose Soft Elastic Actor-Critic (SEAC), a novel off-policy actor-critic algorithm to address this is…

Computationally Efficient Unsupervised Deep Learning for Robust Joint AP Clustering and Beamforming Design in Cell-Free Systems
Guanghui Chen, Zheng Wang, Hongxin Lin, Yongming Huang, Luxi Yang
https://arxiv.org/abs/2404.02531

Computationally Efficient Unsupervised Deep Learning for Robust Joint AP Clustering and Beamforming Design in Cell-Free Systems
In this paper, we consider robust joint access point (AP) clustering and beamforming design with imperfect channel state information (CSI) in cell-free systems. Specifically, we jointly optimize AP clustering and beamforming with imperfect CSI to simultaneously maximize the worst-case sum rate and minimize the number of AP clustering under power constraint and the sparsity constraint of AP clustering. By transformations, the semi-infinite constraints caused by the imperfect CSI are converted in…

This https://arxiv.org/abs/2403.18742 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Understanding the Learning Dynamics of Alignment with Human Feedback
Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these methods affect model behavior remains an open question. Our work provides an initial attempt to theoretically analyze the learning dynamics of human preference alignment. We formally show how the distribution of preference datasets influences the rate of mod…

How to Privately Tune Hyperparameters in Federated Learning? Insights from a Benchmark Study
Natalija Mitic, Apostolos Pyrgelis, Sinem Sav
https://arxiv.org/abs/2402.16087

How to Privately Tune Hyperparameters in Federated Learning? Insights from a Benchmark Study
In this paper, we address the problem of privacy-preserving hyperparameter (HP) tuning for cross-silo federated learning (FL). We first perform a comprehensive measurement study that benchmarks various HP strategies suitable for FL. Our benchmarks show that the optimal parameters of the FL server, e.g., the learning rate, can be accurately and efficiently tuned based on the HPs found by each client on its local data. We demonstrate that HP averaging is suitable for iid settings, while density-b…

Transfer Learning from Whisper for Microscopic Intelligibility Prediction
Paul Best, Santiago Cuervo, Ricard Marxer
https://arxiv.org/abs/2404.01737 https:…

Transfer Learning from Whisper for Microscopic Intelligibility Prediction
Macroscopic intelligibility models predict the expected human word-error-rate for a given speech-in-noise stimulus. In contrast, microscopic intelligibility models aim to make fine-grained predictions about listeners' perception, e.g. predicting phonetic or lexical responses. State-of-the-art macroscopic models use transfer learning from large scale deep learning models for speech processing, whereas such methods have rarely been used for microscopic modeling. In this paper, we study the use of…

New Pathways in Neutrino Physics via Quantum-Encoded Data Analysis
Jeffrey Lazar, Santiago Giner Olavarrieta, Giancarlo Gatti, Carlos A. Arg\"uelles, Mikel Sanz
https://arxiv.org/abs/2402.19306

New Pathways in Neutrino Physics via Quantum-Encoded Data Analysis
Ever-increasing amount of data is produced by particle detectors in their quest to unveil the laws of Nature. The large data rate requires the use of specialized triggers that promptly reduce the data rate to a manageable level; however, in doing so, unexpected new phenomena may escape detection. Additionally, the large data rate is increasingly difficult to analyze effectively, which has led to a recent revolution on machine learning techniques. Here, we present a methodology based on recent q…

This https://arxiv.org/abs/2401.09286 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deployable Reinforcement Learning with Variable Control Rate
Deploying controllers trained with Reinforcement Learning (RL) on real robots can be challenging: RL relies on agents' policies being modeled as Markov Decision Processes (MDPs), which assume an inherently discrete passage of time. The use of MDPs results in that nearly all RL-based control systems employ a fixed-rate control strategy with a period (or time step) typically chosen based on the developer's experience or specific characteristics of the application environment. Unfortunately, the s…

Learning-Based Joint Beamforming and Antenna Movement Design for Movable Antenna Systems
Caihao Weng, Yuanbin Chen, Lipeng Zhu, Ying Wang
https://arxiv.org/abs/2404.01784

Learning-Based Joint Beamforming and Antenna Movement Design for Movable Antenna Systems
In this paper, we investigate a multi-receiver communication system enabled by movable antennas (MAs). Specifically, the transmit beamforming and the double-side antenna movement at the transceiver are jointly designed to maximize the sum-rate of all receivers under imperfect channel state information (CSI). Since the formulated problem is non-convex with highly coupled variables, conventional optimization methods cannot solve it efficiently. To address these challenges, an effective learning-b…

This https://arxiv.org/abs/2306.11172 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Deep Learning-based Auto-encoder for Time-offset Faster-than-Nyquist Downlink NOMA with Timing Errors and Imperfect CSI
We examine encoding and decoding of transmitted sequences for the downlink time-offset faster than Nyquist signaling non-orthogonal multiple access NOMA (T-NOMA) channel. We employ a previously proposed singular value decomposition (SVD)-based scheme as a benchmark. While this SVD scheme provides reliable communication, our findings reveal that it is not optimal in terms of bit error rate (BER). Additionally, the SVD is sensitive to timing offset errors, and its time complexity increases quadra…

This https://arxiv.org/abs/2401.09286 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deployable Reinforcement Learning with Variable Control Rate
Deploying controllers trained with Reinforcement Learning (RL) on real robots can be challenging: RL relies on agents' policies being modeled as Markov Decision Processes (MDPs), which assume an inherently discrete passage of time. The use of MDPs results in that nearly all RL-based control systems employ a fixed-rate control strategy with a period (or time step) typically chosen based on the developer's experience or specific characteristics of the application environment. Unfortunately, the s…

This https://arxiv.org/abs/2303.08028 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

EdgeServe: A Streaming System for Decentralized Model Serving
The relevant features for a machine learning task may arrive as one or more continuous streams of data. Serving machine learning models over streams of data creates a number of interesting systems challenges in managing data routing, time-synchronization, and rate control. This paper presents EdgeServe, a distributed streaming system that can serve predictions from machine learning models in real time. We evaluate EdgeServe on three streaming prediction tasks: (1) human activity recognition, (2…

This https://arxiv.org/abs/2310.14085 has been replaced.
link: https://scholar.google.com/scholar?q=a

Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback
Online gradient descent (OGD) is well known to be doubly optimal under strong convexity or monotonicity assumptions: (1) in the single-agent setting, it achieves an optimal regret of $Θ(\log T)$ for strongly convex cost functions; and (2) in the multi-agent setting of strongly monotone games, with each agent employing OGD, we obtain last-iterate convergence of the joint action to a unique Nash equilibrium at an optimal rate of $Θ(\frac{1}{T})$. While these finite-time guarantees highlight its…

This https://arxiv.org/abs/2111.04597 has been replaced.
link: https://scholar.google.com/scholar?q=a

Neyman-Pearson Multi-class Classification via Cost-sensitive Learning
Most existing classification methods aim to minimize the overall misclassification error rate. However, in applications such as loan default prediction, different types of errors can have varying consequences. To address this asymmetry issue, two popular paradigms have been developed: the Neyman-Pearson (NP) paradigm and the cost-sensitive (CS) paradigm. Previous studies on the NP paradigm have primarily focused on the binary case, while the multi-class NP problem poses a greater challenge due …

Machine learning?: Definitely useful. AI?: Unclear. https://hbr.org/2023/06/the-ai-hype-cycle-is-distracting-companies

The AI Hype Cycle Is Distracting Companies
Machine learning has an “AI” problem. With new breathtaking capabilities from generative AI released every several months — and AI hype escalating at an even higher rate — it’s high time we differentiate most of today’s practical ML projects from those research advances. This begins by correctly naming such projects: Call them “ML,” not “AI.” Including all ML initiatives under the “AI” umbrella oversells and misleads, contributing to a high failure rate for ML business d…

Finding Decision Tree Splits in Streaming and Massively Parallel Models
Huy Pham, Hoang Ta, Hoa T. Vu
https://arxiv.org/abs/2403.19867 https://

Finding Decision Tree Splits in Streaming and Massively Parallel Models
In this work, we provide data stream algorithms that compute optimal splits in decision tree learning. In particular, given a data stream of observations $x_i$ and their labels $y_i$, the goal is to find the optimal split point $j$ that divides the data into two sets such that the mean squared error (for regression) or misclassification rate (for classification) is minimized. We provide various fast streaming algorithms that use sublinear space and a small number of passes for these problems. T…

Neural Optimizer Equation, Decay Function, and Learning Rate Schedule Joint Evolution
Brandon Morgan, Dean Hougen
https://arxiv.org/abs/2404.06679 https://…

Neural Optimizer Equation, Decay Function, and Learning Rate Schedule Joint Evolution
A major contributor to the quality of a deep learning model is the selection of the optimizer. We propose a new dual-joint search space in the realm of neural optimizer search (NOS), along with an integrity check, to automate the process of finding deep learning optimizers. Our dual-joint search space simultaneously allows for the optimization of not only the update equation, but also internal decay functions and learning rate schedules for optimizers. We search the space using our proposed mut…

Deep Learning-Based Speech and Vision Synthesis to Improve Phishing Attack Detection through a Multi-layer Adaptive Framework
Tosin Ige, Christopher Kiekintveld, Aritran Piplai
https://arxiv.org/abs/2402.17249

Deep Learning-Based Speech and Vision Synthesis to Improve Phishing Attack Detection through a Multi-layer Adaptive Framework
The ever-evolving ways attacker continues to im prove their phishing techniques to bypass existing state-of-the-art phishing detection methods pose a mountain of challenges to researchers in both industry and academia research due to the inability of current approaches to detect complex phishing attack. Thus, current anti-phishing methods remain vulnerable to complex phishing because of the increasingly sophistication tactics adopted by attacker coupled with the rate at which new tactics are be…

This https://arxiv.org/abs/2308.01562 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Hierarchical Federated Learning in Wireless Networks: Pruning Tackles Bandwidth Scarcity and System Heterogeneity
While a practical wireless network has many tiers where end users do not directly communicate with the central server, the users' devices have limited computation and battery powers, and the serving base station (BS) has a fixed bandwidth. Owing to these practical constraints and system models, this paper leverages model pruning and proposes a pruning-enabled hierarchical federated learning (PHFL) in heterogeneous networks (HetNets). We first derive an upper bound of the convergence rate that c…

Universal Lower Bounds and Optimal Rates: Achieving Minimax Clustering Error in Sub-Exponential Mixture Models
Maximilien Dreveton, Alperen G\"ozeten, Matthias Grossglauser, Patrick Thiran
https://arxiv.org/abs/2402.15432

Universal Lower Bounds and Optimal Rates: Achieving Minimax Clustering Error in Sub-Exponential Mixture Models
Clustering is a pivotal challenge in unsupervised machine learning and is often investigated through the lens of mixture models. The optimal error rate for recovering cluster labels in Gaussian and sub-Gaussian mixture models involves ad hoc signal-to-noise ratios. Simple iterative algorithms, such as Lloyd's algorithm, attain this optimal error rate. In this paper, we first establish a universal lower bound for the error rate in clustering any mixture model, expressed through a Chernoff diverg…

This https://arxiv.org/abs/2206.00814 has been replaced.
link: https://scholar.google.com/scholar?q=a

Extremely Fast Convergence Rates for Extremum Seeking Control with Polyak-Ruppert Averaging
Stochastic approximation is a foundation for many algorithms found in machine learning and optimization. It is in general slow to converge: the mean square error vanishes as $O(n^{-1})$. A deterministic counterpart known as quasi-stochastic approximation is a viable alternative in many applications, including gradient-free optimization and reinforcement learning. It was assumed in prior research that the optimal achievable convergence rate is $O(n^{-2})$. It is shown in this paper that through …

Integrating Deep Learning and Synthetic Biology: A Co-Design Approach for Enhancing Gene Expression via N-terminal Coding Sequences
Zhanglu Yan, Weiran Chu, Yuhua Sheng, Kaiwen Tang, Shida Wang, Yanfeng Liu, Weng-Fai Wong
https://arxiv.org/abs/2402.13297

Integrating Deep Learning and Synthetic Biology: A Co-Design Approach for Enhancing Gene Expression via N-terminal Coding Sequences
N-terminal coding sequence (NCS) influences gene expression by impacting the translation initiation rate. The NCS optimization problem is to find an NCS that maximizes gene expression. The problem is important in genetic engineering. However, current methods for NCS optimization such as rational design and statistics-guided approaches are labor-intensive yield only relatively small improvements. This paper introduces a deep learning/synthetic biology co-designed few-shot training workflow for N…

FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks
Bingnan Xiao, Jingjing Zhang, Wei Ni, Xin Wang
https://arxiv.org/abs/2404.14811

FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks
Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE (FLARE) framework to mitigate the impact of the heterogeneity. The key idea is to allow the participating devices to adjust their individual learning rates and local training iterations, adapting to their instantaneous computing powers. The convergence upper b…

Optimal Refund Mechanism with Consumer Learning
Qianjun Lyu
https://arxiv.org/abs/2404.14927 https://arxiv.org/pdf/2404.14927<…

Optimal Refund Mechanism with Consumer Learning
This paper studies the optimal refund mechanism when an uninformed buyer can privately acquire information about his valuation of a product over time. We consider a class of refund mechanisms based on stochastic return policies: if the buyer requests a return, the seller will issue a (partial) refund while allowing the buyer to keep the product with some probability. Such return policies can affect the buyer's learning process and thereby influence the return rate. Nevertheless, we show that th…

Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories
Ning Yang, Shuo Chen, Haijun Zhang, Randall Berry
https://arxiv.org/abs/2404.14238

Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories
Mobile Edge Computing (MEC) broadens the scope of computation and storage beyond the central network, incorporating edge nodes close to end devices. This expansion facilitates the implementation of large-scale "connected things" within edge networks. The advent of applications necessitating real-time, high-quality service presents several challenges, such as low latency, high data rate, reliability, efficiency, and security, all of which demand resolution. The incorporation of reinforcement lea…

Modular Blind Video Quality Assessment
Wen Wen, Mu Li, Yabin Zhang, Yiting Liao, Junlin Li, Li Zhang, Kede Ma
https://arxiv.org/abs/2402.19276 https://

Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze the video content in its aggressively downsampled format, while being blind to the impact of actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model, and a method of training it to improve its modularity. Spec…

Constraints on prospective deviations from the cold dark matter model using a Gaussian Process
Martiros Khurshudyan, Emilio Elizalde
https://arxiv.org/abs/2402.08630

Constraints on prospective deviations from the cold dark matter model using a Gaussian Process
Recently, using Bayesian Machine Learning, a deviation from the cold dark matter model on cosmological scales has been put forward. Such model might replace a proposed non-gravitational interaction between dark energy and dark matter, and help solve the $H_{0}$ tension problem. The idea behind the learning procedure relied there on a generated expansion rate, while the real expansion rate was just used to validate the learned results. In the present work, however, the emphasis is put on a Gauss…

This https://arxiv.org/abs/2402.04798 has been replaced.
link: https://scholar.google.com/scholar?q=a

Spiking-PhysFormer: Camera-Based Remote Photoplethysmography with Parallel Spike-driven Transformer
Artificial neural networks (ANNs) can help camera-based remote photoplethysmography (rPPG) in measuring cardiac activity and physiological signals from facial videos, such as pulse wave, heart rate and respiration rate with better accuracy. However, most existing ANN-based methods require substantial computing resources, which poses challenges for effective deployment on mobile devices. Spiking neural networks (SNNs), on the other hand, hold immense potential for energy-efficient deep learning …

Understanding the Learning Dynamics of Alignment with Human Feedback
Shawn Im, Yixuan Li
https://arxiv.org/abs/2403.18742 https://arx…

Understanding the Learning Dynamics of Alignment with Human Feedback
Aligning large language models (LLMs) with human intentions has become a critical task for safely deploying models in real-world systems. While existing alignment approaches have seen empirical success, theoretically understanding how these methods affect model behavior remains an open question. Our work provides an initial attempt to theoretically analyze the learning dynamics of human preference alignment. We formally show how the distribution of preference datasets influences the rate of mod…

This https://arxiv.org/abs/2403.06418 has been replaced.
initial toot: https://mastoxiv.page/@ar…

Efficient Estimation of the Convective Cooling Rate of Photovoltaic Arrays with Various Geometric Configurations: a Physics-Informed Machine Learning Approach
Convective heat transfer is crucial for photovoltaic (PV) systems, as the power generation of PV is sensitive to temperature. The configuration of PV arrays have a significant impact on convective heat transfer by influencing turbulent characteristics. Conventional methods of quantifying the configuration effects are either through Computational Fluid Dynamics (CFD) simulations or empirical methods, which face the challenge of either high computational demand or low accuracy, especially when co…

A physics-constrained deep learning surrogate model of the runaway electron avalanche growth rate
Jonathan S. Arnaud, Tyler Mark, Christopher J. McDevitt
https://arxiv.org/abs/2403.04948

A physics-constrained deep learning surrogate model of the runaway electron avalanche growth rate
A surrogate model of the runaway electron avalanche growth rate in a magnetic fusion plasma is developed. This is accomplished by employing a physics-informed neural network (PINN) to learn the parametric solution of the adjoint to the relativistic Fokker-Planck equation. The resulting PINN is able to evaluate the runaway probability function across a broad range of parameters in the absence of any synthetic or experimental data. This surrogate of the adjoint relativistic Fokker-Planck equation…

Distributed Source Coding for Parametric and Non-Parametric Regression
Jiahui Wei, Elsa Dupraz, Philippe Mary
https://arxiv.org/abs/2404.18688 https://

Distributed Source Coding for Parametric and Non-Parametric Regression
The design of communication systems dedicated to machine learning tasks is one key aspect of goal-oriented communications. In this framework, this article investigates the interplay between data reconstruction and learning from the same compressed observations, particularly focusing on the regression problem. We establish achievable rate-generalization error regions for both parametric and non-parametric regression, where the generalization error measures the regression performance on previousl…

This https://arxiv.org/abs/2307.07572 has been replaced.
initial toot: https://mastoxiv.page/@arX…

High-Rate Phase Association with Travel Time Neural Fields
Our understanding of regional seismicity from multi-station seismograms relies on the ability to associate arrival phases with their originating earthquakes. Deep-learning-based phase detection now detects small, high-rate arrivals from seismicity clouds, even at negative magnitudes. This new data could give important insight into earthquake dynamics, but it is presents a challenging association task. Existing techniques relying on coarsely approximated, fixed wave speed models fail in this une…

Unveiling the Impact of Macroeconomic Policies: A Double Machine Learning Approach to Analyzing Interest Rate Effects on Financial Markets
Anoop Kumar, Suresh Dodda, Navin Kamuni, Rajeev Kumar Arora
https://arxiv.org/abs/2404.07225

Unveiling the Impact of Macroeconomic Policies: A Double Machine Learning Approach to Analyzing Interest Rate Effects on Financial Markets
This study examines the effects of macroeconomic policies on financial markets using a novel approach that combines Machine Learning (ML) techniques and causal inference. It focuses on the effect of interest rate changes made by the US Federal Reserve System (FRS) on the returns of fixed income and equity funds between January 1986 and December 2021. The analysis makes a distinction between actively and passively managed funds, hypothesizing that the latter are less susceptible to changes in in…

Remaining Energy Prediction for Lithium-Ion Batteries: A Machine Learning Approach
Hao Tu, Manashita Borah, Scott Moura, Yebin Wang, Huazhen Fang
https://arxiv.org/abs/2404.14767 …

Remaining Energy Prediction for Lithium-Ion Batteries: A Machine Learning Approach
Lithium-ion batteries have found their way into myriad sectors of industry to drive electrification, decarbonization, and sustainability. A crucial aspect in ensuring their safe and optimal performance is monitoring their energy state. In this paper, we present the first study on predicting the remaining energy of a battery cell undergoing discharge over wide current ranges from low to high C-rates. The complexity of the challenge arises from the cell's C-rate-dependent energy availability as w…

Integrating Deep Learning and Synthetic Biology: A Co-Design Approach for Enhancing Gene Expression via N-terminal Coding Sequences
Zhanglu Yan, Weiran Chu, Yuhua Sheng, Kaiwen Tang, Shida Wang, Yanfeng Liu, Weng-Fai Wong
https://arxiv.org/abs/2402.13297

Integrating Deep Learning and Synthetic Biology: A Co-Design Approach for Enhancing Gene Expression via N-terminal Coding Sequences
N-terminal coding sequence (NCS) influences gene expression by impacting the translation initiation rate. The NCS optimization problem is to find an NCS that maximizes gene expression. The problem is important in genetic engineering. However, current methods for NCS optimization such as rational design and statistics-guided approaches are labor-intensive yield only relatively small improvements. This paper introduces a deep learning/synthetic biology co-designed few-shot training workflow for N…

This https://arxiv.org/abs/2204.05382 has been replaced.
link: https://scholar.google.com/scholar?q=a

Modeling and Contractivity of Neural-Synaptic Networks with Hebbian Learning
This paper is concerned with the modeling and analysis of two of the most commonly used recurrent neural network models (i.e., Hopfield neural network and firing-rate neural network) with dynamic recurrent connections undergoing Hebbian learning rules. To capture the synaptic sparsity of neural circuits we propose a low dimensional formulation. We then characterize certain key dynamical properties. First, we give biologically-inspired forward invariance results. Then, we give sufficient conditi…

An Effective Networks Intrusion Detection Approach Based on Hybrid Harris Hawks and Multi-Layer Perceptron
Moutaz Alazab, Ruba Abu Khurma, Pedro A. Castillo, Bilal Abu-Salih, Alejandro Martin, David Camacho
https://arxiv.org/abs/2402.14037 https://arxiv.org/pdf/2402.14037
arXiv:2402.14037v1 Announce Type: new
Abstract: This paper proposes an Intrusion Detection System (IDS) employing the Harris Hawks Optimization algorithm (HHO) to optimize Multilayer Perceptron learning by optimizing bias and weight parameters. HHO-MLP aims to select optimal parameters in its learning process to minimize intrusion detection errors in networks. HHO-MLP has been implemented using EvoloPy NN framework, an open-source Python tool specialized for training MLPs using evolutionary algorithms. For purposes of comparing the HHO model against other evolutionary methodologies currently available, specificity and sensitivity measures, accuracy measures, and mse and rmse measures have been calculated using KDD datasets. Experiments have demonstrated the HHO MLP method is effective at identifying malicious patterns. HHO-MLP has been tested against evolutionary algorithms like Butterfly Optimization Algorithm (BOA), Grasshopper Optimization Algorithms (GOA), and Black Widow Optimizations (BOW), with validation by Random Forest (RF), XG-Boost. HHO-MLP showed superior performance by attaining top scores with accuracy rate of 93.17%, sensitivity level of 89.25%, and specificity percentage of 95.41%.

On the Convergence Rate of the Stochastic Gradient Descent (SGD) and application to a modified policy gradient for the Multi Armed Bandit
Stefana Anita, Gabriel Turinici
https://arxiv.org/abs/2402.06388

On the Convergence Rate of the Stochastic Gradient Descent (SGD) and application to a modified policy gradient for the Multi Armed Bandit
We present a self-contained proof of the convergence rate of the Stochastic Gradient Descent (SGD) when the learning rate follows an inverse time decays schedule; we next apply the results to the convergence of a modified form of policy gradient Multi-Armed Bandit (MAB) with $L2$ regularization.

This https://arxiv.org/abs/2307.16798 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Forster-Warmuth Counterfactual Regression: A Unified Learning Approach
Series or orthogonal basis regression is one of the most popular non-parametric regression techniques in practice, obtained by regressing the response on features generated by evaluating the basis functions at observed covariate values. The most routinely used series estimator is based on ordinary least squares fitting, which is known to be minimax rate optimal in various settings, albeit under stringent restrictions on the basis functions and the distribution of covariates. In this work, inspi…

This https://arxiv.org/abs/2311.03821 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Positive Competitive Networks for Sparse Reconstruction
We propose and analyze a continuous-time firing-rate neural network, the positive firing-rate competitive network (\pfcn), to tackle sparse reconstruction problems with non-negativity constraints. These problems, which involve approximating a given input stimulus from a dictionary using a set of sparse (active) neurons, play a key role in a wide range of domains, including for example neuroscience, signal processing, and machine learning. First, by leveraging the theory of proximal operators, w…

This https://arxiv.org/abs/2306.00673 has been replaced.
link: https://scholar.google.com/scholar?q=a

Attribute-Efficient PAC Learning of Low-Degree Polynomial Threshold Functions with Nasty Noise
The concept class of low-degree polynomial threshold functions (PTFs) plays a fundamental role in machine learning. In this paper, we study PAC learning of $K$-sparse degree-$d$ PTFs on $\mathbb{R}^n$, where any such concept depends only on $K$ out of $n$ attributes of the input. Our main contribution is a new algorithm that runs in time $({nd}/ε)^{O(d)}$ and under the Gaussian marginal distribution, PAC learns the class up to error rate $ε$ with $O(\frac{K^{4d}}{ε^{2d}} \cdot \log^{5d} n)$ …

$\widetilde{O}(T^{-1})$ Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games
Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew Kalbarczyk, Tamer Ba\c{s}ar
https://arxiv.org/abs/2403.07890

$\widetilde{O}(T^{-1})$ Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games
No-regret learning has a long history of being closely connected to game theory. Recent works have devised uncoupled no-regret learning dynamics that, when adopted by all the players in normal-form games, converge to various equilibrium solutions at a near-optimal rate of $\widetilde{O}(T^{-1})$, a significant improvement over the $O(1/\sqrt{T})$ rate of classic no-regret learners. However, analogous convergence results are scarce in Markov games, a more generic setting that lays the foundation…

This take on solar power is correct. And the same reasoning applies to batteries, which if anything are dropping in price even faster than PVs (it’s a less mature industry). https://caseyhandmer.wordpress.com/2023/10/11/radical-energy-abundance/

Radical Energy Abundance
Originally published at Roots of Progress, based on this thread. Everyone knows the industrial revolution occurred centuries ago and involved steam engines. That was just the warm up. We are now a …

Deep Learning Based Multi-Node ISAC 4D Environmental Reconstruction with Uplink- Downlink Cooperation
Bohao Lu, Zhiqing Wei, Huici Wu, Xinrui Zeng, Lin Wang, Xi Lu, Dongyang Mei, Zhiyong Feng
https://arxiv.org/abs/2404.14862

Deep Learning Based Multi-Node ISAC 4D Environmental Reconstruction with Uplink- Downlink Cooperation
Utilizing widely distributed communication nodes to achieve environmental reconstruction is one of the significant scenarios for Integrated Sensing and Communication (ISAC) and a crucial technology for 6G. To achieve this crucial functionality, we propose a deep learning based multi-node ISAC 4D environment reconstruction method with Uplink-Downlink (UL-DL) cooperation, which employs virtual aperture technology, Constant False Alarm Rate (CFAR) detection, and Mutiple Signal Classification (MUSI…

Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications
Puze Liu, Haitham Bou-Ammar, Jan Peters, Davide Tateo
https://arxiv.org/abs/2404.09080

Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications
Integrating learning-based techniques, especially reinforcement learning, into robotics is promising for solving complex problems in unstructured environments. However, most existing approaches are trained in well-tuned simulators and subsequently deployed on real robots without online fine-tuning. In this setting, the simulation's realism seriously impacts the deployment's success rate. Instead, learning with real-world interaction data offers a promising alternative: not only eliminates the n…

New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning
Yonghong Yao, Lateef O. Jolaoso, Yekini Shehu, Jen-Chih Yao
https://arxiv.org/abs/2404.14800

New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning
In this work, we propose some new Douglas-Rashford splitting algorithms for solving a class of generalized DC (difference of convex functions) in real Hilbert spaces. The proposed methods leverage the proximal properties of the nonsmooth component and a fasten control parameter which improves the convergence rate of the algorithms. We prove the convergence of these methods to the critical points of nonconvex optimization under reasonable conditions. We evaluate the performance and effectiveness…

An Effective Networks Intrusion Detection Approach Based on Hybrid Harris Hawks and Multi-Layer Perceptron
Moutaz Alazab, Ruba Abu Khurma, Pedro A. Castillo, Bilal Abu-Salih, Alejandro Martin, David Camacho
https://arxiv.org/abs/2402.14037 https://arxiv.org/pdf/2402.14037
arXiv:2402.14037v1 Announce Type: new
Abstract: This paper proposes an Intrusion Detection System (IDS) employing the Harris Hawks Optimization algorithm (HHO) to optimize Multilayer Perceptron learning by optimizing bias and weight parameters. HHO-MLP aims to select optimal parameters in its learning process to minimize intrusion detection errors in networks. HHO-MLP has been implemented using EvoloPy NN framework, an open-source Python tool specialized for training MLPs using evolutionary algorithms. For purposes of comparing the HHO model against other evolutionary methodologies currently available, specificity and sensitivity measures, accuracy measures, and mse and rmse measures have been calculated using KDD datasets. Experiments have demonstrated the HHO MLP method is effective at identifying malicious patterns. HHO-MLP has been tested against evolutionary algorithms like Butterfly Optimization Algorithm (BOA), Grasshopper Optimization Algorithms (GOA), and Black Widow Optimizations (BOW), with validation by Random Forest (RF), XG-Boost. HHO-MLP showed superior performance by attaining top scores with accuracy rate of 93.17%, sensitivity level of 89.25%, and specificity percentage of 95.41%.

Investigating the Robustness of Vision Transformers against Label Noise in Medical Image Classification
Bidur Khanal, Prashant Shrestha, Sanskar Amgain, Bishesh Khanal, Binod Bhattarai, Cristian A. Linte
https://arxiv.org/abs/2402.16734

Investigating the Robustness of Vision Transformers against Label Noise in Medical Image Classification
Label noise in medical image classification datasets significantly hampers the training of supervised deep learning methods, undermining their generalizability. The test performance of a model tends to decrease as the label noise rate increases. Over recent years, several methods have been proposed to mitigate the impact of label noise in medical image classification and enhance the robustness of the model. Predominantly, these works have employed CNN-based architectures as the backbone of thei…

Selecting informative conformal prediction sets with false coverage rate control
Ulysse Gazin, Ruth Heller, Ariane Marandon, Etienne Roquain
https://arxiv.org/abs/2403.12295

Selecting informative conformal prediction sets with false coverage rate control
In supervised learning, including regression and classification, conformal methods provide prediction sets for the outcome/label with finite sample coverage for any machine learning predictors. We consider here the case where such prediction sets come after a selection process. The selection process requires that the selected prediction sets be `informative' in a well defined sense. We consider both the classification and regression settings where the analyst may consider as informative only th…

This https://arxiv.org/abs/2307.07572 has been replaced.
initial toot: https://mastoxiv.page/@arX…

High-Rate Phase Association with Travel Time Neural Fields
Our understanding of regional seismicity from multi-station seismograms relies on the ability to associate arrival phases with their originating earthquakes. Deep-learning-based phase detection now detects small, high-rate arrivals from seismicity clouds, even at negative magnitudes. This new data could give important insight into earthquake dynamics, but it is presents a challenging association task. Existing techniques relying on coarsely approximated, fixed wave speed models fail in this une…

Unveiling the Impact of Macroeconomic Policies: A Double Machine Learning Approach to Analyzing Interest Rate Effects on Financial Markets
Anoop Kumar, Suresh Dodda, Navin Kamuni, Rajeev Kumar Arora
https://arxiv.org/abs/2404.07225

Unveiling the Impact of Macroeconomic Policies: A Double Machine Learning Approach to Analyzing Interest Rate Effects on Financial Markets
This study examines the effects of macroeconomic policies on financial markets using a novel approach that combines Machine Learning (ML) techniques and causal inference. It focuses on the effect of interest rate changes made by the US Federal Reserve System (FRS) on the returns of fixed income and equity funds between January 1986 and December 2021. The analysis makes a distinction between actively and passively managed funds, hypothesizing that the latter are less susceptible to changes in in…

Efficient Estimation of the Convective Cooling Rate of Photovoltaic Arrays with Various Geometric Configurations: a Physics-Informed Machine Learning Approach
Dapeng Wang, Zhaojian Liang, Ziqi Zhang, Mengying Li
https://arxiv.org/abs/2403.06418

Efficient Estimation of the Convective Cooling Rate of Photovoltaic Arrays with Various Geometric Configurations: a Physics-Informed Machine Learning Approach
Convective heat transfer is crucial for photovoltaic (PV) systems, as the power generation of PV is sensitive to temperature. The configuration of PV arrays have a significant impact on convective heat transfer by influencing turbulent characteristics. Conventional methods of quantifying the configuration effects are either through Computational Fluid Dynamics (CFD) simulations or empirical methods, which face the challenge of either high computational demand or low accuracy, especially when co…

This https://arxiv.org/abs/2402.19306 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_hepe…

New Pathways in Neutrino Physics via Quantum-Encoded Data Analysis
Ever-increasing amount of data is produced by particle detectors in their quest to unveil the laws of Nature. The large data rate requires the use of specialized triggers that promptly reduce the data rate to a manageable level; however, in doing so, unexpected new phenomena may escape detection. Additionally, the large data rate is increasingly difficult to analyze effectively, which has led to a recent revolution on machine learning techniques. Here, we present a methodology based on recent q…

Improving Line Search Methods for Large Scale Neural Network Training
Philip Kenneweg, Tristan Kenneweg, Barbara Hammer
https://arxiv.org/abs/2403.18519 ht…

Improving Line Search Methods for Large Scale Neural Network Training
In recent studies, line search methods have shown significant improvements in the performance of traditional stochastic gradient descent techniques, eliminating the need for a specific learning rate schedule. In this paper, we identify existing issues in state-of-the-art line search methods, propose enhancements, and rigorously evaluate their effectiveness. We test these methods on larger datasets and more complex data domains than before. Specifically, we improve the Armijo line search by inte…

Deep Joint CSI Feedback and Multiuser Precoding for MIMO OFDM Systems
Yiran Guo, Wei Chen, Jialong Xu, Lun Li, Bo Ai
https://arxiv.org/abs/2404.16289 https…

Deep Joint CSI Feedback and Multiuser Precoding for MIMO OFDM Systems
The design of precoding plays a crucial role in achieving a high downlink sum-rate in multiuser multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) systems. In this correspondence, we propose a deep learning based joint CSI feedback and multiuser precoding method in frequency division duplex systems, aiming at maximizing the downlink sum-rate performance in an end-to-end manner. Specifically, the eigenvectors of the CSI matrix are compressed using deep joint …

$\widetilde{O}(T^{-1})$ Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games
Weichao Mao, Haoran Qiu, Chen Wang, Hubertus Franke, Zbigniew Kalbarczyk, Tamer Ba\c{s}ar
https://arxiv.org/abs/2403.07890

$\widetilde{O}(T^{-1})$ Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games
No-regret learning has a long history of being closely connected to game theory. Recent works have devised uncoupled no-regret learning dynamics that, when adopted by all the players in normal-form games, converge to various equilibrium solutions at a near-optimal rate of $\widetilde{O}(T^{-1})$, a significant improvement over the $O(1/\sqrt{T})$ rate of classic no-regret learners. However, analogous convergence results are scarce in Markov games, a more generic setting that lays the foundation…

UAV-enabled Collaborative Beamforming via Multi-Agent Deep Reinforcement Learning
Saichao Liu, Geng Sun, Jiahui Li, Shuang Liang, Qingqing Wu, Pengfei Wang, Dusit Niyato
https://arxiv.org/abs/2404.07453

UAV-enabled Collaborative Beamforming via Multi-Agent Deep Reinforcement Learning
In this paper, we investigate an unmanned aerial vehicle (UAV)-assistant air-to-ground communication system, where multiple UAVs form a UAV-enabled virtual antenna array (UVAA) to communicate with remote base stations by utilizing collaborative beamforming. To improve the work efficiency of the UVAA, we formulate a UAV-enabled collaborative beamforming multi-objective optimization problem (UCBMOP) to simultaneously maximize the transmission rate of the UVAA and minimize the energy consumption o…

This https://arxiv.org/abs/2211.08597 has been replaced.
link: https://scholar.google.com/scholar?q=a

SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
SketchySGD improves upon existing stochastic gradient methods in machine learning by using randomized low-rank approximations to the subsampled Hessian and by introducing an automated stepsize that works well across a wide range of convex machine learning problems. We show theoretically that SketchySGD with a fixed stepsize converges linearly to a small ball around the optimum. Further, in the ill-conditioned setting we show SketchySGD converges at a faster rate than SGD for least-squares probl…

This https://arxiv.org/abs/2310.16139 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Pix2HDR -- A pixel-wise acquisition and deep learning-based synthesis approach for high-speed HDR videos
Accurately capturing dynamic scenes with wide-ranging motion and light intensity is crucial for many vision applications. However, acquiring high-speed high dynamic range (HDR) video is challenging because the camera's frame rate restricts its dynamic range. Existing methods sacrifice speed to acquire multi-exposure frames. Yet, misaligned motion in these frames can still pose complications for HDR fusion algorithms, resulting in artifacts. Instead of frame-based exposures, we sample the videos…

This https://arxiv.org/abs/2311.03821 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qbi…

Positive Competitive Networks for Sparse Reconstruction
We propose and analyze a continuous-time firing-rate neural network, the positive firing-rate competitive network (\pfcn), to tackle sparse reconstruction problems with non-negativity constraints. These problems, which involve approximating a given input stimulus from a dictionary using a set of sparse (active) neurons, play a key role in a wide range of domains, including for example neuroscience, signal processing, and machine learning. First, by leveraging the theory of proximal operators, w…

Multi-Objective Deep Reinforcement Learning for 5G Base Station Placement to Support Localisation for Future Sustainable Traffic
Ahmed Al-Tahmeesschi, Jukka Talvitie, Miguel L\'opez-Ben\'itez, Hamed Ahmadi, Laura Ruotsalainen
https://arxiv.org/abs/2404.14954

Multi-Objective Deep Reinforcement Learning for 5G Base Station Placement to Support Localisation for Future Sustainable Traffic
Millimeter-wave (mmWave) is a key enabler for next-generation transportation systems. However, in an urban city scenario, mmWave is highly susceptible to blockages and shadowing. Therefore, base station (BS) placement is a crucial task in the infrastructure design where coverage requirements need to be met while simultaneously supporting localisation. This work assumes a pre-deployed BS and another BS is required to be added to support both localisation accuracy and coverage rate in an urban ci…

This https://arxiv.org/abs/2401.07644 has been replaced.
link: https://scholar.google.com/scholar?q=a

Resource Allocation in STAR-RIS-Aided SWIPT with RSMA via Meta-Learning
Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) is a cutting-edge concept for the sixth-generation (6G) wireless networks. In this letter, we propose a novel system that incorporates STAR-RIS with simultaneous wireless information and power transfer (SWIPT) using rate splitting multiple access (RSMA). The proposed system facilitates communication from a multi-antenna base station (BS) to single-antenna users in a downlink transmission. The BS concurrentl…

Re-pseudonymization Strategies for Smart Meter Data Are Not Robust to Deep Learning Profiling Attacks
Ana-Maria Cretu, Miruna Rusu, Yves-Alexandre de Montjoye
https://arxiv.org/abs/2404.03948

Re-pseudonymization Strategies for Smart Meter Data Are Not Robust to Deep Learning Profiling Attacks
Smart meters, devices measuring the electricity and gas consumption of a household, are currently being deployed at a fast rate throughout the world. The data they collect are extremely useful, including in the fight against climate change. However, these data and the information that can be inferred from them are highly sensitive. Re-pseudonymization, i.e., the frequent replacement of random identifiers over time, is widely used to share smart meter data while mitigating the risk of re-identif…

This https://arxiv.org/abs/2204.08989 has been replaced.
link: https://scholar.google.com/scholar?q=a

Efficient Deep Learning-based Estimation of the Vital Signs on Smartphones
With the increasing use of smartphones in our daily lives, these devices have become capable of performing many complex tasks. Concerning the need for continuous monitoring of vital signs, especially for the elderly or those with certain types of diseases, the development of algorithms that can estimate vital signs using smartphones has attracted researchers worldwide. In particular, researchers have been exploring ways to estimate vital signs, such as heart rate, oxygen saturation levels, and …

Rate-Optimal Non-Asymptotics for the Quadratic Prediction Error Method
Charis Stamouli, Ingvar Ziemann, George J. Pappas
https://arxiv.org/abs/2404.07937 h…

Rate-Optimal Non-Asymptotics for the Quadratic Prediction Error Method
We study the quadratic prediction error method -- i.e., nonlinear least squares -- for a class of time-varying parametric predictor models satisfying a certain identifiability condition. While this method is known to asymptotically achieve the optimal rate for a wide range of problems, there have been no non-asymptotic results matching these optimal rates outside of a select few, typically linear, model classes. By leveraging modern tools from learning with dependent data, we provide the first …

Efficient Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
A. Martina Neuman, Philipp Christian Petersen
https://arxiv.org/abs/2404.04549

Efficient Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders
We study the learning problem associated with spiking neural networks. Specifically, we consider hypothesis sets of spiking neural networks with affine temporal encoders and decoders and simple spiking neurons having only positive synaptic weights. We demonstrate that the positivity of the weights continues to enable a wide range of expressivity results, including rate-optimal approximation of smooth functions or approximation without the curse of dimensionality. Moreover, positive-weight spiki…

Deep Reinforcement Learning Enhanced Rate-Splitting Multiple Access for Interference Mitigation
Osman Nuri Irkicatal, Elif Tugce Ceran, Melda Yuksel
https://arxiv.org/abs/2403.05974

Deep Reinforcement Learning Enhanced Rate-Splitting Multiple Access for Interference Mitigation
This study explores the application of the rate-splitting multiple access (RSMA) technique, vital for interference mitigation in modern communication systems. It investigates the use of precoding methods in RSMA, especially in complex multiple-antenna interference channels, employing deep reinforcement learning. The aim is to optimize precoders and power allocation for common and private data streams involving multiple decision-makers. A multi-agent deep deterministic policy gradient (MADDPG) f…

This https://arxiv.org/abs/2403.19867 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…

Finding Decision Tree Splits in Streaming and Massively Parallel Models
In this work, we provide data stream algorithms that compute optimal splits in decision tree learning. In particular, given a data stream of observations $x_i$ and their labels $y_i$, the goal is to find the optimal split point $j$ that divides the data into two sets such that the mean squared error (for regression) or misclassification rate (for classification) is minimized. We provide various fast streaming algorithms that use sublinear space and a small number of passes for these problems. T…

Real-world Instance-specific Image Goal Navigation for Service Robots: Bridging the Domain Gap with Contrastive Learning
Taichi Sakaguchi, Akira Taniguchi, Yoshinobu Hagiwara, Lotfi El Hafi, Shoichi Hasegawa, Tadahiro Taniguchi
https://arxiv.org/abs/2404.09645

Real-world Instance-specific Image Goal Navigation for Service Robots: Bridging the Domain Gap with Contrastive Learning
Improving instance-specific image goal navigation (InstanceImageNav), which locates the identical object in a real-world environment from a query image, is essential for robotic systems to assist users in finding desired objects. The challenge lies in the domain gap between low-quality images observed by the moving robot, characterized by motion blur and low-resolution, and high-quality query images provided by the user. Such domain gaps could significantly reduce the task success rate but have…

Q-learning-based Joint Design of Adaptive Modulation and Precoding for Physical Layer Security in Visible Light Communications
Duc M. T. Hoang, Thanh V. Pham, Anh T. Pham, Chuyen T Nguyen
https://arxiv.org/abs/2402.13549

Q-learning-based Joint Design of Adaptive Modulation and Precoding for Physical Layer Security in Visible Light Communications
There has been an increasing interest in physical layer security (PLS), which, compared with conventional cryptography, offers a unique approach to guaranteeing information confidentiality against eavesdroppers. In this paper, we study a joint design of adaptive $M$-ary pulse amplitude modulation (PAM) and precoding, which aims to optimize wiretap visible-light channels' secrecy capacity and bit error rate (BER) performances. The proposed design is motivated by higher-order modulation, which re…

Learned Finite-Time Consensus for Distributed Optimization
Aaron Fainman, Stefan Vlaski
https://arxiv.org/abs/2404.07018 https://arxi…

Learned Finite-Time Consensus for Distributed Optimization
Most algorithms for decentralized learning employ a consensus or diffusion mechanism to drive agents to a common solution of a global optimization problem. Generally this takes the form of linear averaging, at a rate of contraction determined by the mixing rate of the underlying network topology. For very sparse graphs this can yield a bottleneck, slowing down the convergence of the learning algorithm. We show that a sequence of matrices achieving finite-time consensus can be learned for unknow…

This https://arxiv.org/abs/2401.00691 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Stochastic Gradient Descent for Additive Nonparametric Regression
This paper introduces an iterative algorithm for training additive models that enjoys favorable memory storage and computational requirements. The algorithm can be viewed as the functional counterpart of stochastic gradient descent, applied to the coefficients of a truncated basis expansion of the component functions. We show that the resulting estimator satisfies an oracle inequality that allows for model mis-specification. In the well-specified setting, by choosing the learning rate carefully…

S2LIC: Learned Image Compression with the SwinV2 Block, Adaptive Channel-wise and Global-inter Attention Context
Yongqiang Wang, Feng Liang, Jie Liang, Haisheng Fu
https://arxiv.org/abs/2403.14471

S2LIC: Learned Image Compression with the SwinV2 Block, Adaptive Channel-wise and Global-inter Attention Context
Recently, deep learning technology has been successfully applied in the field of image compression, leading to superior rate-distortion performance. It is crucial to design an effective and efficient entropy model to estimate the probability distribution of the latent representation. However, the majority of entropy models primarily focus on one-dimensional correlation processing between channel and spatial information. In this paper, we propose an Adaptive Channel-wise and Global-inter attenti…

This https://arxiv.org/abs/2404.07937 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Rate-Optimal Non-Asymptotics for the Quadratic Prediction Error Method
We study the quadratic prediction error method -- i.e., nonlinear least squares -- for a class of time-varying parametric predictor models satisfying a certain identifiability condition. While this method is known to asymptotically achieve the optimal rate for a wide range of problems, there have been no non-asymptotic results matching these optimal rates outside of a select few, typically linear, model classes. By leveraging modern tools from learning with dependent data, we provide the first …

This https://arxiv.org/abs/2305.03571 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Model-free Reinforcement Learning of Semantic Communication by Stochastic Policy Gradient
Following the recent success of Machine Learning tools in wireless communications, the idea of semantic communication by Weaver from 1949 has gained attention. It breaks with Shannon's classic design paradigm by aiming to transmit the meaning, i.e., semantics, of a message instead of its exact version, allowing for information rate savings. In this work, we apply the Stochastic Policy Gradient (SPG) to design a semantic communication system by reinforcement learning, separating transmitter and …

This https://arxiv.org/abs/2402.00389 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm
Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension. This paper considers the classical RMSProp and its momentum extension and establishes the convergence rate of $\frac{1}{T}\sum_{k=1}^T E\left[\|\nabla f(x^k)\|_1\right]\leq O(\frac{\sqrt{d}C}{T^{1/4}})$ measured by $\ell_1$ norm without the bounded gradient assum…

This https://arxiv.org/abs/2311.10678 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

Distilling and Retrieving Generalizable Knowledge for Robot Manipulation via Language Corrections
Today's robot policies exhibit subpar performance when faced with the challenge of generalizing to novel environments. Human corrective feedback is a crucial form of guidance to enable such generalization. However, adapting to and learning from online human corrections is a non-trivial endeavor: not only do robots need to remember human feedback over time to retrieve the right information in new settings and reduce the intervention rate, but also they would need to be able to respond to feedbac…

This https://arxiv.org/abs/2304.10985 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

RSBA: Robust Statistical Backdoor Attack under Privilege-Constrained Scenarios
Learning-based systems have been demonstrated to be vulnerable to backdoor attacks, wherein malicious users manipulate model performance by injecting backdoors into the target model and activating them with specific triggers. Previous backdoor attack methods primarily focused on two key metrics: attack success rate and stealthiness. However, these methods often necessitate significant privileges over the target model, such as control over the training process, making them challenging to impleme…

Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems
Junyong Shin, Yujin Kang, Yo-Seb Jeon
https://arxiv.org/abs/2403.07355 htt…

Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems
This paper presents a finite-rate deep-learning (DL)-based channel state information (CSI) feedback method for massive multiple-input multiple-output (MIMO) systems. The presented method provides a finite-bit representation of the latent vector based on a vector-quantized variational autoencoder (VQ-VAE) framework while reducing its computational complexity based on shape-gain vector quantization. In this method, the magnitude of the latent vector is quantized using a non-uniform scalar codeboo…

This https://arxiv.org/abs/2402.00389 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm
Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension. This paper considers the classical RMSProp and its momentum extension and establishes the convergence rate of $\frac{1}{T}\sum_{k=1}^T E\left[\|\nabla f(x^k)\|_1\right]\leq O(\frac{\sqrt{d}C}{T^{1/4}})$ measured by $\ell_1$ norm without the bounded gradient assum…

This https://arxiv.org/abs/2310.14751 has been replaced.
link: https://scholar.google.com/scholar?q=a

Efficient and Interpretable Bandit Algorithms
Motivated by the importance of explainability in modern machine learning, we design bandit algorithms that are efficient and interpretable. A bandit algorithm is interpretable if it explores with the objective of reducing uncertainty in the unknown model parameter. To quantify the interpretability, we introduce a novel metric of model error, which compares the rate reduction of the mean reward estimates to their actual means among all the plausible actions. We propose CODE, a bandit algorithm b…

This https://arxiv.org/abs/2403.08505 has been replaced.
link: https://scholar.google.com/scholar?q=a

Content-aware Masked Image Modeling Transformer for Stereo Image Compression
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, which leads to suboptimal rate-distortion results. In this paper, we propose a stereo image compression framework, named CAMSIC. CAMSIC independently transforms each image to latent representation and…

Graph Neural Network Meets Multi-Agent Reinforcement Learning: Fundamentals, Applications, and Future Directions
Ziheng Liu (Sherman), Jiayi Zhang (Sherman), Enyu Shi (Sherman), Zhilong Liu (Sherman), Dusit Niyato (Sherman), Bo Ai (Sherman), Xuemin (Sherman), Shen
https://arxiv.org/abs/2404.04898…

Graph Neural Network Meets Multi-Agent Reinforcement Learning: Fundamentals, Applications, and Future Directions
Multi-agent reinforcement learning (MARL) has become a fundamental component of next-generation wireless communication systems. Theoretically, although MARL has the advantages of low computational complexity and fast convergence rate, there exist several challenges including partial observability, non-stationary, and scalability. In this article, we investigate a novel MARL with graph neural network-aided communication (GNNComm-MARL) to address the aforementioned challenges by making use of gra…

PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformer
Xingyu Su, Xiaojie Zhu, Yang Li, Yong Li, Chi Chen, Paulo Esteves-Ver\'issimo
https://arxiv.org/abs/2404.04886

PagPassGPT: Pattern Guided Password Guessing via Generative Pretrained Transformer
Amidst the surge in deep learning-based password guessing models, challenges of generating high-quality passwords and reducing duplicate passwords persist. To address these challenges, we present PagPassGPT, a password guessing model constructed on Generative Pretrained Transformer (GPT). It can perform pattern guided guessing by incorporating pattern structure information as background knowledge, resulting in a significant increase in the hit rate. Furthermore, we propose D&C-GEN to reduce the…

This https://arxiv.org/abs/2401.00587 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Brain Tumor Segmentation Based on Deep Learning, Attention Mechanisms, and Energy-Based Uncertainty Prediction
Brain tumors are one of the deadliest forms of cancer with a mortality rate of over 80%. A quick and accurate diagnosis is crucial to increase the chance of survival. However, in medical analysis, the manual annotation and segmentation of a brain tumor can be a complicated task. Multiple MRI modalities are typically analyzed as they provide unique information regarding the tumor regions. Although these MRI modalities are helpful for segmenting gliomas, they tend to increase overfitting and comp…

This https://arxiv.org/abs/2402.00389 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm
Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension. This paper considers the classical RMSProp and its momentum extension and establishes the convergence rate of $\frac{1}{T}\sum_{k=1}^T E\left[\|\nabla f(x^k)\|_1\right]\leq O(\frac{\sqrt{d}C}{T^{1/4}})$ measured by $\ell_1$ norm without the bounded gradient assum…

This https://arxiv.org/abs/2403.07355 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems
This paper presents a finite-rate deep-learning (DL)-based channel state information (CSI) feedback method for massive multiple-input multiple-output (MIMO) systems. The presented method provides a finite-bit representation of the latent vector based on a vector-quantized variational autoencoder (VQ-VAE) framework while reducing its computational complexity based on shape-gain vector quantization. In this method, the magnitude of the latent vector is quantized using a non-uniform scalar codeboo…

This https://arxiv.org/abs/2403.07355 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Vector Quantization for Deep-Learning-Based CSI Feedback in Massive MIMO Systems
This paper presents a finite-rate deep-learning (DL)-based channel state information (CSI) feedback method for massive multiple-input multiple-output (MIMO) systems. The presented method provides a finite-bit representation of the latent vector based on a vector-quantized variational autoencoder (VQ-VAE) framework while reducing its computational complexity based on shape-gain vector quantization. In this method, the magnitude of the latent vector is quantized using a non-uniform scalar codeboo…

This https://arxiv.org/abs/2305.17283 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Sharpened Lazy Incremental Quasi-Newton Method
The problem of minimizing the sum of $n$ functions in $d$ dimensions is ubiquitous in machine learning and statistics. In many applications where the number of observations $n$ is large, it is necessary to use incremental or stochastic methods, as their per-iteration cost is independent of $n$. Of these, Quasi-Newton (QN) methods strike a balance between the per-iteration cost and the convergence rate. Specifically, they exhibit a superlinear rate with $O(d^2)$ cost in contrast to the linear ra…

This https://arxiv.org/abs/2305.17283 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Sharpened Lazy Incremental Quasi-Newton Method
The problem of minimizing the sum of $n$ functions in $d$ dimensions is ubiquitous in machine learning and statistics. In many applications where the number of observations $n$ is large, it is necessary to use incremental or stochastic methods, as their per-iteration cost is independent of $n$. Of these, Quasi-Newton (QN) methods strike a balance between the per-iteration cost and the convergence rate. Specifically, they exhibit a superlinear rate with $O(d^2)$ cost in contrast to the linear ra…

This https://arxiv.org/abs/2302.14336 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIT_…

Beamforming and Device Selection Design in Federated Learning with Over-the-air Aggregation
Federated learning (FL) with over-the-air computation can efficiently utilize the communication bandwidth but is susceptible to analog aggregation error. Excluding those devices with weak channel conditions can reduce the aggregation error, but it also limits the amount of local training data for FL, which can reduce the training convergence rate. In this work, we jointly design uplink receiver beamforming and device selection for over-the-air FL over time-varying wireless channels to maximize …

UAV-Assisted Enhanced Coverage and Capacity in Dynamic MU-mMIMO IoT Systems: A Deep Reinforcement Learning Approach
MohammadMahdi Ghadaksaz, Mobeen Mahmood, Tho Le-Ngoc
https://arxiv.org/abs/2404.06726

UAV-Assisted Enhanced Coverage and Capacity in Dynamic MU-mMIMO IoT Systems: A Deep Reinforcement Learning Approach
This study focuses on a multi-user massive multiple-input multiple-output (MU-mMIMO) system by incorporating an unmanned aerial vehicle (UAV) as a decode-and-forward (DF) relay between the base station (BS) and multiple Internet-of-Things (IoT) devices. Our primary objective is to maximize the overall achievable rate (AR) by introducing a novel framework that integrates joint hybrid beamforming (HBF) and UAV localization in dynamic MU-mMIMO IoT systems. Particularly, HBF stages for BS and UAV a…

This https://arxiv.org/abs/2402.19276 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Modular Blind Video Quality Assessment
Blind video quality assessment (BVQA) plays a pivotal role in evaluating and improving the viewing experience of end-users across a wide range of video-based platforms and services. Contemporary deep learning-based models primarily analyze the video content in its aggressively downsampled format, while being blind to the impact of actual spatial resolution and frame rate on video quality. In this paper, we propose a modular BVQA model, and a method of training it to improve its modularity. Spec…

This https://arxiv.org/abs/2212.00927 has been replaced.
link: https://scholar.google.com/scholar?q=a

First-Order Methods for Nonsmooth Nonconvex Functional Constrained Optimization with or without Slater Points
Constrained optimization problems where both the objective and constraints may be nonsmooth and nonconvex arise across many learning and data science settings. In this paper, we show for any Lipschitz, weakly convex objectives and constraints, a simple first-order method finds a feasible, $ε$-stationary point at a convergence rate of $O(ε^{-4})$ without relying on compactness or Constraint Qualification (CQ). When CQ holds, this convergence is measured by approximately satisfying the Karush-K…