Tootfinder

Rate optimal learning of equilibria from data
Till Freihaut, Luca Viano, Emanuele Nevali, Volkan Cevher, Matthieu Geist, Giorgia Ramponi
https://arxiv.org/abs/2510.09325 https:/…

Rate optimal learning of equilibria from data
We close open theoretical gaps in Multi-Agent Imitation Learning (MAIL) by characterizing the limits of non-interactive MAIL and presenting the first interactive algorithm with near-optimal sample complexity. In the non-interactive setting, we prove a statistical lower bound that identifies the all-policy deviation concentrability coefficient as the fundamental complexity measure, and we show that Behavior Cloning (BC) is rate-optimal. For the interactive setting, we introduce a framework that …

Learning to Transmit Over Unknown Erasure Channels with Empirical Erasure Rate Feedback
Haricharan Balasundaram, Krishna Jagannathan
https://arxiv.org/abs/2507.08599

Learning to Transmit Over Unknown Erasure Channels with Empirical Erasure Rate Feedback
We address the problem of reliable data transmission within a finite time horizon $T$ over a binary erasure channel with unknown erasure probability. We consider a feedback model wherein the transmitter can query the receiver infrequently and obtain the empirical erasure rate experienced by the latter. We aim to minimize a regret quantity, i.e. how much worse a strategy performs compared to an oracle who knows the probability of erasure, while operating at the same block error rate. A learning …

Membership Inference Attacks with False Discovery Rate Control
Chenxu Zhao, Wei Qian, Aobo Chen, Mengdi Huai
https://arxiv.org/abs/2508.07066 https://arxiv…

Membership Inference Attacks with False Discovery Rate Control
Recent studies have shown that deep learning models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. To analyze and study these vulnerabilities, various MIA methods have been proposed. Despite the significance and popularity of MIAs, existing works on MIAs are limited in providing guarantees on the false discovery rate (FDR), which refers to the expected proportion of false discoveries among the identified p…

Energy distance and evolution problems: a promising tool for kinetic equations
Gennaro Auricchio, Giuseppe Toscani
https://arxiv.org/abs/2510.09123 https://

Energy distance and evolution problems: a promising tool for kinetic equations
We study the rate of convergence to equilibrium of the solutions to Fokker-Planck type equations with linear drift by means of Cramér and Energy distances, which have been recently widely used in problems related to AI, in particular for tasks related to machine learning. In all cases in which the Fokker-Planck type equations can be treated through these distances, it is shown that the rate of decay is improved with respect to known results which are based on the decay of relative entropy.

AI-Augmented Visible Light Communication: A Framework for Noise Mitigation and Secure Data Transmission
A. A. Nutfaji, Moustafa Hassan Elmallah
https://arxiv.org/abs/2507.08145

AI-Augmented Visible Light Communication: A Framework for Noise Mitigation and Secure Data Transmission
This paper presents a proposed AI Deep Learning model that addresses common challenges encountered in Visible Light Communication (VLC) systems. In this work, we run a Python simulation that models a basic VLC system primarily affected by Additive White Gaussian Noise (AWGN). A Deep Neural Network (DNN) is then trained to equalize the noisy signal received and improve signal integrity. The system evaluates and compares the Bit Error Rate (BER) before and after equalization to demonstrate the ef…

Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence
Yuxing Liu, Yuze Ge, Rui Pan, An Kang, Tong Zhang
https://arxiv.org/abs/2509.07972 https://

Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence
Learning rate warmup is a popular and practical technique in training large-scale deep neural networks. Despite the huge success in practice, the theoretical advantages of this strategy of gradually increasing the learning rate at the beginning of the training process have not been fully understood. To resolve this gap between theory and practice, we first propose a novel family of generalized smoothness assumptions, and validate its applicability both theoretically and empirically. Under the n…

Hierarchical Placement Learning for Network Slice Provisioning
Jesutofunmi Ajayi, Antonio Di Maio, Torsten Braun
https://arxiv.org/abs/2508.06432 https://a…

Hierarchical Placement Learning for Network Slice Provisioning
In this work, we aim to address the challenge of slice provisioning in edge-based mobile networks. We propose a solution that learns a service function chain placement policy for Network Slice Requests, to maximize the request acceptance rate, while minimizing the average node resource utilization. To do this, we consider a Hierarchical Multi-Armed Bandit problem and propose a two-level hierarchical bandit solution which aims to learn a scalable placement policy that optimizes the stated object…

Leveraging transfer learning for accurate estimation of ionic migration barriers in solids
Reshma Devi, Keith T. Butler, Gopalakrishnan Sai Gautam
https://arxiv.org/abs/2508.06436

Leveraging transfer learning for accurate estimation of ionic migration barriers in solids
Ionic mobility determines the rate performance of several applications, such as batteries, fuel cells, and electrochemical sensors and is exponentially dependent on the migration barrier ($E_m$), a difficult to measure/calculate quantity. Previous approaches to identify materials with high ionic mobility have relied on imprecise descriptors given the lack of generalizable models to predict $E_m$. Here, we present a graph neural network based architecture that leverages principles of transfer le…

MotionSwap
Om Patil, Jinesh Modi, Suryabha Mukhopadhyay, Meghaditya Giri, Chhavi Malhotra
https://arxiv.org/abs/2508.06430 https://arxiv.org/pdf/2508.06430…

MotionSwap
Face swapping technology has gained significant attention in both academic research and commercial applications. This paper presents our implementation and enhancement of SimSwap, an efficient framework for high fidelity face swapping. We introduce several improvements to the original model, including the integration of self and cross-attention mechanisms in the generator architecture, dynamic loss weighting, and cosine annealing learning rate scheduling. These enhancements lead to significant …

LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
Jiahao Zhao
https://arxiv.org/abs/2508.03275 https://arxiv.org/pdf…

LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
Spaced repetition systems are fundamental to efficient learning and memory retention, but existing algorithms often struggle with semantic interference and personalized adaptation. We present LECTOR (\textbf{L}LM-\textbf{E}nhanced \textbf{C}oncept-based \textbf{T}est-\textbf{O}riented \textbf{R}epetition), a novel adaptive scheduling algorithm specifically designed for test-oriented learning scenarios, particularly language examinations where success rate is paramount. LECTOR leverages large la…

Anticipating AMOC transitions via deep learning
Wenjie Zhang, Yu Huang, Sebastian Bathiany, Yechul Shin, Maya Ben-Yami, Suiping Zhou, Niklas Boers
https://arxiv.org/abs/2509.06450

Anticipating AMOC transitions via deep learning
Key components of the Earth system can undergo abrupt and potentially irreversible transitions when the magnitude or rate of external forcing exceeds critical thresholds. In this study, we use the example of the Atlantic Meridional Overturning Circulation (AMOC) to demonstrate the challenges associated with anticipating such transitions when the system is susceptible to bifurcation-induced, rate-induced, and noise-induced tipping. Using a calibrated AMOC box model, we conduct large ensemble sim…

Adaptive Deception Framework with Behavioral Analysis for Enhanced Cybersecurity Defense
Basil Abdullah AL-Zahrani
https://arxiv.org/abs/2510.02424 https://

Adaptive Deception Framework with Behavioral Analysis for Enhanced Cybersecurity Defense
This paper presents CADL (Cognitive-Adaptive Deception Layer), an adaptive deception framework achieving 99.88% detection rate with 0.13% false positive rate on the CICIDS2017 dataset. The framework employs ensemble machine learning (Random Forest, XGBoost, Neural Networks) combined with behavioral profiling to identify and adapt responses to network intrusions. Through a coordinated signal bus architecture, security components share real-time intelligence, enabling collective decision-making. …

Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
Brian Hu Zhang, Ioannis Anagnostides, Tuomas Sandholm
https://arxiv.org/abs/2510.04407

Scale-Invariant Regret Matching and Online Learning with Optimal Convergence: Bridging Theory and Practice in Zero-Sum Games
A considerable chasm has been looming for decades between theory and practice in zero-sum game solving through first-order methods. Although a convergence rate of $T^{-1}$ has long been established since Nemirovski's mirror-prox algorithm and Nesterov's excessive gap technique in the early 2000s, the most effective paradigm in practice is *counterfactual regret minimization*, which is based on *regret matching* and its modern variants. In particular, the state of the art across most benchmarks …

Learning from the past in an irreversible investment problem
Topias Tolonen-Weckstr\"om
https://arxiv.org/abs/2508.21731 https://arxiv.org/pdf/2508.21…

Learning from the past in an irreversible investment problem
We consider an irreversible investment problem under incomplete information, where the investor is able to exercise multiple investment rights to a project. The investor does not observe the project value directly and instead only a noisy observation process is observed. Upon each investment, the investor acquires previously hidden information from the project's past (''learning from the past''), and so the learning rate of the problem is controlled by investing. The acquisition of additional i…

Machine Learning-Driven Performance Analysis of Compressed Communication in Aerial-RIS Networks for Future 6G Networks
Muhammad Farhan Khan, Muhammad Ahmed Mohsin, Zeeshan Alam, Muhammad Saad, Muhammad Waqar
https://arxiv.org/abs/2508.01911

Machine Learning-Driven Performance Analysis of Compressed Communication in Aerial-RIS Networks for Future 6G Networks
In the future 6G and wireless networks, particularly in dense urban environments, bandwidth exhaustion and limited capacity pose significant challenges to enhancing data rates. We introduce a novel system model designed to improve the data rate of users in next-generation multi-cell networks by integrating Unmanned Aerial Vehicle (UAV)-Assisted Reconfigurable Intelligent Surfaces (RIS), Non-Orthogonal Multiple Access (NOMA), and Coordinated Multipoint Transmission (CoMP). Optimally deploying Ae…

Temperature derivative divergence of the electric conductivity and thermal photon emission rate at the critical end point from holography
Yi-Ping Si, Danning Li, Mei Huang
https://arxiv.org/abs/2509.25636

Temperature derivative divergence of the electric conductivity and thermal photon emission rate at the critical end point from holography
The thermal photon emission rate $\frac{dΓ}{dk}$ and DC eletric conductivity $σ_{Q}$ of the strongly coupled quark-gluon plasma (sQGP) are investigated around the critical end point in a $N_f=2+1$ holographic QCD model with parameters obtained from machine-learning. It is found that both thermal photon emission rate and eletric conductivity grow most obviously around $T_c$, which agrees with the previous studies, and the result of eletric conductivity at zero chemical potential resembles the …

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/2]:
- On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
Bal\'azs Csan\'ad Cs\'aji, L\'aszl\'o Gy\"orfi, Ambrus Tam\'as, Harro Walk

Graph Learning for Foreign Exchange Rate Prediction and Statistical Arbitrage
Yoonsik Hong, Diego Klabjan
https://arxiv.org/abs/2508.14784 https://arxiv.or…

Graph Learning for Foreign Exchange Rate Prediction and Statistical Arbitrage
We propose a two-step graph learning approach for foreign exchange statistical arbitrages (FXSAs), addressing two key gaps in prior studies: the absence of graph-learning methods for foreign exchange rate prediction (FXRP) that leverage multi-currency and currency-interest rate relationships, and the disregard of the time lag between price observation and trade execution. In the first step, to capture complex multi-currency and currency-interest rate relationships, we formulate FXRP as an edge-…

Physics-informed learning under mixing: How physical knowledge speeds up learning
Anna Scampicchio, Leonardo F. Toso, Rahel Rickenbach, James Anderson, Melanie N. Zeilinger
https://arxiv.org/abs/2509.24801

Physics-informed learning under mixing: How physical knowledge speeds up learning
A major challenge in physics-informed machine learning is to understand how the incorporation of prior domain knowledge affects learning rates when data are dependent. Focusing on empirical risk minimization with physics-informed regularization, we derive complexity-dependent bounds on the excess risk in probability and in expectation. We prove that, when the physical prior information is aligned, the learning rate improves from the (slow) Sobolev minimax rate to the (fast) optimal i.i.d. one w…

False Discovery Rate Control via Bayesian Mirror Statistic
Marco Molinari, Magne Thoresen
https://arxiv.org/abs/2510.00875 https://arxiv.org/pdf/2510.00875…

False Discovery Rate Control via Bayesian Mirror Statistic
Simultaneously performing variable selection and inference in high-dimensional models is an open challenge in statistics and machine learning. The increasing availability of vast amounts of variables requires the adoption of specific statistical procedures to accurately select the most important predictors in a high-dimensional space, while being able to control some form of selection error. In this work we adapt the Mirror Statistic approach to False Discovery Rate (FDR) control into a Bayesia…

Activity propagation with Hebbian learning
Will T. Engedal, R\'obert Juh\'asz, Istv\'an A. Kov\'acs
https://arxiv.org/abs/2508.21053 https://

Activity propagation with Hebbian learning
We investigate the impact of Hebbian learning on the contact process, a paradigmatic model for infection spreading, which has been also proposed as a simple model to capture the dynamics of inter-regional brain activity propagation as well as population spreading. Each of these contexts calls for an extension of the contact process with local learning. We introduce Hebbian learning as a positive or negative reinforcement of the activation rate between a pair of sites after each successful activ…

Deep Learning-Based Rate-Adaptive CSI Feedback for Wideband XL-MIMO Systems in the Near-Field Domain
Zhenyu Liu, Yi Ma, Rahim Tafazolli
https://arxiv.org/abs/2508.00626 https://…

Deep Learning-Based Rate-Adaptive CSI Feedback for Wideband XL-MIMO Systems in the Near-Field Domain
Accurate and efficient channel state information (CSI) feedback is crucial for unlocking the substantial spectral efficiency gains of extremely large-scale MIMO (XL-MIMO) systems in future 6G networks. However, the combination of near-field spherical wave propagation and frequency-dependent beam split effects in wideband scenarios poses significant challenges for CSI representation and compression. This paper proposes WideNLNet-CA, a rate-adaptive deep learning framework designed to enable effi…

Efficient Deep Neural Receiver with Post-Training Quantization
SaiKrishna Saketh Yellapragada, Esa Ollila, Mario Costa
https://arxiv.org/abs/2508.06275 https://

Efficient Deep Neural Receiver with Post-Training Quantization
Deep learning has recently garnered significant interest in wireless communications due to its superior performance compared to traditional model-based algorithms. Deep convolutional neural networks (CNNs) have demonstrated notable improvements in block error rate (BLER) under various channel models and mobility scenarios. However, the high computational complexity and resource demands of deep CNNs pose challenges for deployment in resource-constrained edge systems. The 3rd Generation Partnersh…

Clustering Wind data at 1 AU to contextualize magnetic reconnection in the solar wind
Francesco Carella, Giovanni Lapenta, Alessandro Bemporad, Stefan Eriksson, Maria Elena Innocenti, Sophia K\"ohne, Jasmina Magdalenic
https://arxiv.org/abs/2508.05579

Clustering Wind data at 1 AU to contextualize magnetic reconnection in the solar wind
Context. Magnetic reconnection events are frequently observed in the solar wind. Understanding the patterns and structures within the solar wind is crucial to put observed magnetic reconnection events into context, since their occurrence rate and properties are likely influenced by solar wind conditions. Aims. We employed unsupervised learning techniques such as self-organizing maps (SOM) and K-Means to cluster and interpret solar wind data at 1 AU for an improved understanding of the conditi…

Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
D. Veerababu, Ashwin A. Raikar, Prasanta K. Ghosh
https://arxiv.org/abs/2507.21749

Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made. The learning rate is one of such crucial hyperparameters, which is usually kept static during the training process. Learning dynamics in complex systems often requires a more adaptive approach to the learning rate. This adaptability becomes crucial to effecti…

Towards a Real-Time Warning System for Detecting Inaccuracies in Photoplethysmography-Based Heart Rate Measurements in Wearable Devices
Rania Islmabouli, Marlene Brunner, Devender Kumar, Mahdi Sareban, Gunnar Treff, Michael Neudorfer, Josef Niebauer, Arne Bathke, Jan David Smeddinck
https://arxiv.org/abs/2508.19818

Towards a Real-Time Warning System for Detecting Inaccuracies in Photoplethysmography-Based Heart Rate Measurements in Wearable Devices
Wearable devices with photoplethysmography (PPG) sensors are widely used to monitor heart rate (HR), yet often suffer from accuracy issues. However, users typically do not receive an indication of potential measurement errors. We present a real-time warning system that detects and communicates inaccuracies in PPG-derived HR, aiming to enhance transparency and trust. Using data from Polar and Garmin devices, we trained a deep learning model to classify HR accuracy using only the derived HR signa…

A literature-derived dataset of migration barriers for quantifying ionic transport in battery materials
Reshma Devi, Avaneesh Balasubramanian, Keith T. Butler, Gopalakrishnan Sai Gautam
https://arxiv.org/abs/2508.06459

A literature-derived dataset of migration barriers for quantifying ionic transport in battery materials
The rate performance of any electrode or solid electrolyte material used in a battery is critically dependent on the migration barrier ($E_m$) governing the motion of the intercalant ion, which is a difficult-to-estimate quantity both experimentally and computationally. The foundation for constructing and validating accurate machine learning (ML) models that are capable of predicting $E_m$, and hence accelerating the discovery of novel electrodes and solid electrolytes, lies in the availability…

Implicit Spatiotemporal Bandwidth Enhancement Filter by Sine-activated Deep Learning Model for Fast 3D Photoacoustic Tomography
I Gede Eka Sulistyawan, Takuro Ishii, Riku Suzuki, Yoshifumi Saijo
https://arxiv.org/abs/2507.20575

Implicit Spatiotemporal Bandwidth Enhancement Filter by Sine-activated Deep Learning Model for Fast 3D Photoacoustic Tomography
3D photoacoustic tomography (3D-PAT) using high-frequency hemispherical transducers offers near-omnidirectional reception and enhanced sensitivity to the finer structural details encoded in the high-frequency components of the broadband photoacoustic (PA) signal. However, practical constraints such as limited number of channels with bandlimited sampling rate often result in sparse and bandlimited sensors that degrade image quality. To address this, we revisit the 2D deep learning (DL) approach …

Herding Prices: Social Learning and Dynamic Competition in Duopoly
Georgy Lukyanov, Ariza Azova
https://arxiv.org/abs/2509.01263 https://arxiv.org/pdf/2509…

Herding Prices: Social Learning and Dynamic Competition in Duopoly
We embed observational learning (BHW) in a symmetric duopoly with random arrivals and search frictions. With fixed posted prices, a mixed-strategy pricing equilibrium exists and yields price dispersion even with ex-ante identical firms. We provide closed-form cascade bands and show wrong cascades occur with positive probability for interior parameters, vanishing as signals become precise or search costs fall; absorption probabilities are invariant to the arrival rate. In equilibrium, the suppor…

Detecting Blinks in Healthy and Parkinson's EEG: A Deep Learning Perspective
Artem Lensky, Yiding Qiu
https://arxiv.org/abs/2509.04951 https://arxiv.or…

Detecting Blinks in Healthy and Parkinson's EEG: A Deep Learning Perspective
Blinks in electroencephalography (EEG) are often treated as unwanted artifacts. However, recent studies have demonstrated that blink rate and its variability are important physiological markers to monitor cognitive load, attention, and potential neurological disorders. This paper addresses the critical task of accurate blink detection by evaluating various deep learning models for segmenting EEG signals into involuntary blinks and non-blinks. We present a pipeline for blink detection using 1, 3…

Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
Ziqiao Yu, Pengfei Sun, Dan F. M. Goodman
https://arxiv.org/abs/2507.16043 https:…

Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
We investigate the extent to which Spiking Neural Networks (SNNs) trained with Surrogate Gradient Descent (Surrogate GD), with and without delay learning, can learn from precise spike timing beyond firing rates. We first design synthetic tasks isolating intra-neuron inter-spike intervals and cross-neuron synchrony under matched spike counts. On more complex spike-based speech recognition datasets (Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC), we construct variants where spi…

Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing
Yang Tang, Ruijie Liu, Yifan Wang, Shiyu Li, Xi Chen
https://arxiv.org/abs/2509.26242 http…

Finetune Once: Decoupling General & Domain Learning with Dynamic Boosted Annealing
Large language models (LLMs) fine-tuning shows excellent implications. However, vanilla fine-tuning methods often require intricate data mixture and repeated experiments for optimal generalization. To address these challenges and streamline the training process, we propose an efficient and universal solution, Dynamic Boosted Annealing (DBA). We obtain a global gradient through zero-learning-rate training on general data, which is subsequently employed for gradient boosting and dynamic training …

Detecting and measuring respiratory events in horses during exercise with a microphone: deep learning vs. standard signal processing
Jeanne I. M. Parmentier (Utrecht University, University of Twente, Inertia Technology B.V), Rhana M. Aarts (Utrecht University), Elin Hernlund (Swedish University of Agricultural Sciences), Marie Rhodin (Swedish University of Agricultural Sciences), Berend Jan van der Zwaag (University of Twente, Inertia Technology B.V)

Detecting and measuring respiratory events in horses during exercise with a microphone: deep learning vs. standard signal processing
Monitoring respiration parameters such as respiratory rate could be beneficial to understand the impact of training on equine health and performance and ultimately improve equine welfare. In this work, we compare deep learning-based methods to an adapted signal processing method to automatically detect cyclic respiratory events and extract the dynamic respiratory rate from microphone recordings during high intensity exercise in Standardbred trotters. Our deep learning models are able to detect …

Why Do We Need Warm-up? A Theoretical Perspective
Foivos Alimisis, Rustem Islamov, Aurelien Lucchi
https://arxiv.org/abs/2510.03164 https://arxiv.org/pdf/2…

Why Do We Need Warm-up? A Theoretical Perspective
Learning rate warm-up - increasing the learning rate at the beginning of training - has become a ubiquitous heuristic in modern deep learning, yet its theoretical foundations remain poorly understood. In this work, we provide a principled explanation for why warm-up improves training. We rely on a generalization of the $(L_0, L_1)$-smoothness condition, which bounds local curvature as a linear function of the loss sub-optimality and exhibits desirable closure properties. We demonstrate both the…

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
Ramy ElMallah, Krish Chhajer, Chi-Guhn Lee
https://arxiv.org/abs/2509.19524 https://

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
Robot learning papers typically report a single binary success rate (SR), which obscures where a policy succeeds or fails along a multi-step manipulation task. We argue that subgoal-level reporting should become routine: for each trajectory, a vector of per-subgoal SRs that makes partial competence visible (e.g., grasp vs. pour). We propose a blueprint for StepEval, a cost-aware plug-in evaluation framework that utilizes vision-language models (VLMs) as automated judges of subgoal outcomes from…

Evolutionary learning of microbial populations in partially predictable environments
Roaa Mohmmed Yagb Omer, Onofrio Mazzarisi, Martina Dal Bello, Jacopo Grilli
https://arxiv.org/abs/2508.00527

Evolutionary learning of microbial populations in partially predictable environments
Populations evolving in fluctuating environments face the fundamental challenge of balancing adaptation to current conditions against preparation for uncertain futures. Here, we study microbial evolution in partially predictable environments using proteome allocation models that capture the trade-off between growth rate and lag time during environmental transitions. We demonstrate that evolution drives populations toward an evolutionary stable allocation strategy that minimizes resource depleti…

ULISSE: Determination of star-formation rate and stellar mass based on the one-shot galaxy imaging technique
Olena Torbaniuk, Lars Doorenbos, Maurizio Paolillo, Stefano Cavuoti, Massimo Brescia, Giuseppe Longo
https://arxiv.org/abs/2507.20365

ULISSE: Determination of star-formation rate and stellar mass based on the one-shot galaxy imaging technique
Modern sky surveys produce vast amounts of observational data, making the application of classical methods for estimating galaxy properties challenging and time-consuming. This challenge can be significantly alleviated by employing automatic machine and deep learning techniques. We propose an implementation of the ULISSE algorithm aimed at determining physical parameters of galaxies, in particular star-formation rates (SFR) and stellar masses ($M_{\ast}$), using only composite-color images. ULI…

Federated Computation of ROC and PR Curves
Xuefeng Xu, Graham Cormode
https://arxiv.org/abs/2510.04979 https://arxiv.org/pdf/2510.04979

Federated Computation of ROC and PR Curves
Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves are fundamental tools for evaluating machine learning classifiers, offering detailed insights into the trade-offs between true positive rate vs. false positive rate (ROC) or precision vs. recall (PR). However, in Federated Learning (FL) scenarios, where data is distributed across multiple clients, computing these curves is challenging due to privacy and communication constraints. Specifically, the server cannot access raw …

Frabjous: Deep Learning Fast Radio Burst Morphologies
Ajay Kumar, Ashish A. Mahabal, Shriharsh P. Tendulkar
https://arxiv.org/abs/2507.14854 https://

Frabjous: Deep Learning Fast Radio Burst Morphologies
The increasing field of view of radio telescopes and improved data processing capabilities have led to a surge in the detection of Fast Radio Bursts (FRBs). The discovery rate of FRBs is already a few per day and is expected to increase rapidly with new surveys coming online. The growing number of events necessitates prioritized follow-up due to limited multi-wavelength resources, requiring rapid and automated classification. In this study, we introduce Frabjous, a deep learning framework for a…

On the Adversarial Robustness of Learning-based Conformal Novelty Detection
Daofu Zhang, Mehrdad Pournaderi, Hanne M. Clifford, Yu Xiang, Pramod K. Varshney
https://arxiv.org/abs/2510.00463

On the Adversarial Robustness of Learning-based Conformal Novelty Detection
This paper studies the adversarial robustness of conformal novelty detection. In particular, we focus on AdaDetect, a powerful learning-based framework for novelty detection with finite-sample false discovery rate (FDR) control. While AdaDetect provides rigorous statistical guarantees under benign conditions, its behavior under adversarial perturbations remains unexplored. We first formulate an oracle attack setting that quantifies the worst-case degradation of FDR, deriving an upper bound that…

Ultra-Reliable Risk-Aggregated Sum Rate Maximization via Model-Aided Deep Learning
Hassaan Hashmi, Spyridon Pougkakiotis, Dionysis Kalogerias
https://arxiv.org/abs/2509.26311 ht…

Ultra-Reliable Risk-Aggregated Sum Rate Maximization via Model-Aided Deep Learning
We consider the problem of maximizing weighted sum rate in a multiple-input single-output (MISO) downlink wireless network with emphasis on user rate reliability. We introduce a novel risk-aggregated formulation of the complex WSR maximization problem, which utilizes the Conditional Value-at-Risk (CVaR) as a functional for enforcing rate (ultra)-reliability over channel fading uncertainty/risk. We establish a WMMSE-like equivalence between the proposed precoding problem and a weighted risk-aver…

All Eyes, no IMU: Learning Flight Attitude from Vision Alone
Jesse J. Hagenaars, Stein Stroobants, Sander M. Bohte, Guido C. H. E. De Croon
https://arxiv.org/abs/2507.11302

All Eyes, no IMU: Learning Flight Attitude from Vision Alone
Vision is an essential part of attitude control for many flying animals, some of which have no dedicated sense of gravity. Flying robots, on the other hand, typically depend heavily on accelerometers and gyroscopes for attitude stabilization. In this work, we present the first vision-only approach to flight control for use in generic environments. We show that a quadrotor drone equipped with a downward-facing event camera can estimate its attitude and rotation rate from just the event stream, e…

SpliDT: Partitioned Decision Trees for Scalable Stateful Inference at Line Rate
Murayyiam Parvez, Annus Zulfiqar, Roman Beltiukov, Shir Landau Feibish, Walter Willinger, Arpit Gupta, Muhammad Shahbaz
https://arxiv.org/abs/2509.00397

SpliDT: Partitioned Decision Trees for Scalable Stateful Inference at Line Rate
Machine learning (ML) is increasingly being deployed in programmable data planes (switches and SmartNICs) to enable real-time traffic analysis, security monitoring, and in-network decision-making. Decision trees (DTs) are particularly well-suited for these tasks due to their interpretability and compatibility with data-plane architectures, i.e., match-action tables (MATs). However, existing in-network DT implementations are constrained by the need to compute all input features upfront, forcing …

Astrophysical or Terrestrial: Machine learning classification of gravitational-wave candidates using multiple-search information
Seiya Tsukamoto, Andrew Toivonen, Holton Griffin, Avyukt Raghuvanshi, Megan Averill, Frank Kerkow, Michael W. Coughlin, Man Leong Chan, Leo Singer
https://arxiv.org/abs/2508.14242…

Astrophysical or Terrestrial: Machine learning classification of gravitational-wave candidates using multiple-search information
Low-latency gravitational-wave alerts provide the greater multi-messenger community with information about the candidate events detected by the International Gravitational-Wave Network (IGWN). Prompt release of data products such as the sky localization, false alarm rate (FAR), and $p_\mathrm{astro}$ values allow astronomers to make informed decisions on which candidate gravitational-wave events merit target of opportunity (ToO) follow-up. However, false alarms, often referred to as "glitches",…

Reconstructing Subnational Labor Indicators in Colombia: An Integrated Machine and Deep Learning Approach
Jaime Vera-Jaramillo
https://arxiv.org/abs/2508.12514 https://

Reconstructing Subnational Labor Indicators in Colombia: An Integrated Machine and Deep Learning Approach
This study proposes a unified multi-stage framework to reconstruct consistent monthly and annual labor indicators for all 33 Colombian departments from 1993 to 2025. The approach integrates temporal disaggregation, time-series splicing and interpolation, statistical learning, and institutional covariates to estimate seven key variables: employment, unemployment, labor force participation (PEA), inactivity, working-age population (PET), total population, and informality rate, including in region…

Convergence Rate of Generalized Nash Equilibrium Learning in Strongly Monotone Games with Linear Constraints
Tatiana Tatarenko, Maryam Kamgarpour
https://arxiv.org/abs/2507.12112 …

Convergence Rate of Generalized Nash Equilibrium Learning in Strongly Monotone Games with Linear Constraints
We consider payoff-based learning of a generalized Nash equilibrium (GNE) in multi-agent systems. Our focus is on games with jointly convex constraints of a linear structure and strongly monotone pseudo-gradients. We present a convergent procedure based on a partial regularization technique and establish the convergence rate of its iterates under one- and two-point payoff-based feedback. To the best of our knowledge, this work is the first one characterizing the convergence speed of iterates to…

A Bio-Inspired Minimal Model for Non-Stationary K-Armed Bandits
Krubeal Danieli, Mikkel Elle Lepper{\o}d
https://arxiv.org/abs/2509.22209 https://arxiv.org…

A Bio-Inspired Minimal Model for Non-Stationary K-Armed Bandits
While reinforcement learning algorithms have made significant progress in solving multi-armed bandit problems, they often lack biological plausibility in architecture and dynamics. Here, we propose a bio-inspired neural model based on interacting populations of rate neurons, drawing inspiration from the orbitofrontal cortex and anterior cingulate cortex. Our model reports robust performance across various stochastic bandit problems, matching the effectiveness of standard algorithms such as Thom…

Generalization Analysis for Classification on Korobov Space
Yuqing Liu
https://arxiv.org/abs/2509.22748 https://arxiv.org/pdf/2509.22748

Generalization Analysis for Classification on Korobov Space
In this paper, the classification algorithm arising from Tikhonov regularization is discussed. The main intention is to derive learning rates for the excess misclassification error according to the convex $η$-norm loss function $ϕ(v)=(1 - v)_{+}^η$, $η\geq1$. Following the argument, the estimation of error under Tsybakov noise conditions is studied. In addition, we propose the rate of $L_p$ approximation of functions from Korobov space $X^{2, p}([-1,1]^{d})$, $1\leq p \leq \infty$, by the s…

ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling
Huishi Luo, Fuzhen Zhuang, Yongchun Zhu, Yiqing Wu, Bo Kang, Ruobing Xie, Feng Xia, Deqing Wang, Jin Dong
https://arxiv.org/abs/2508.16573

ORCA: Mitigating Over-Reliance for Multi-Task Dwell Time Prediction with Causal Decoupling
Dwell time (DT) is a critical post-click metric for evaluating user preference in recommender systems, complementing the traditional click-through rate (CTR). Although multi-task learning is widely adopted to jointly optimize DT and CTR, we observe that multi-task models systematically collapse their DT predictions to the shortest and longest bins, under-predicting the moderate durations. We attribute this moderate-duration bin under-representation to over-reliance on the CTR-DT spurious correl…

SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation
Paul Grimal, Micha\"el Soumm, Herv\'e Le Borgne, Olivier Ferret, Akihiro Sugimoto
https://arxiv.org/abs/2508.13866

SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation
State-of-the-art text-to-image models produce visually impressive results but often struggle with precise alignment to text prompts, leading to missing critical elements or unintended blending of distinct concepts. We propose a novel approach that learns a high-success-rate distribution conditioned on a target prompt, ensuring that generated images faithfully reflect the corresponding prompts. Our method explicitly models the signal component during the denoising process, offering fine-grained …

When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
Xiang Li, Zebang Shen, Ya-Ping Hsieh, Niao He
https://arxiv.org/abs/2509.24912 https://

When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
Score-based methods, such as diffusion models and Bayesian inverse problems, are often interpreted as learning the data distribution in the low-noise limit ($σ\to 0$). In this work, we propose an alternative perspective: their success arises from implicitly learning the data manifold rather than the full distribution. Our claim is based on a novel analysis of scores in the small-$σ$ regime that reveals a sharp separation of scales: information about the data manifold is $Θ(σ^{-2})$ stronger…

Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling
Peng Yang, Zhengdong Huang, Zicheng Xie, Wentao Tian, Jingyu Liu, Lunhong Dong
https://arxiv.org/abs/2508.21785

Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling
Heart rate prediction is vital for personalized health monitoring and fitness, while it frequently faces a critical challenge when deploying in real-world: data heterogeneity. We classify it in two key dimensions: source heterogeneity from fragmented device markets with varying feature sets, and user heterogeneity reflecting distinct physiological patterns across individuals and activities. Existing methods either discard device-specific information, or fail to model user-specific differences, …

Efficient Breast and Ovarian Cancer Classification via ViT-Based Preprocessing and Transfer Learning
Richa Rawat, Faisal Ahmed
https://arxiv.org/abs/2509.18553 https://

CleanCTG: A Deep Learning Model for Multi-Artefact Detection and Reconstruction in Cardiotocography
Sheng Wong, Beth Albert, Gabriel Davis Jones
https://arxiv.org/abs/2508.10928

CleanCTG: A Deep Learning Model for Multi-Artefact Detection and Reconstruction in Cardiotocography
Cardiotocography (CTG) is essential for fetal monitoring but is frequently compromised by diverse artefacts which obscure true fetal heart rate (FHR) patterns and can lead to misdiagnosis or delayed intervention. Current deep-learning approaches typically bypass comprehensive noise handling, applying minimal preprocessing or focusing solely on downstream classification, while traditional methods rely on simple interpolation or rule-based filtering that addresses only missing samples and fail to…

Programmable Data Planes for Network Security
Gursimran Singh, H. B. Acharya, Minseok Kwon
https://arxiv.org/abs/2507.22165 https://arxiv.org/pdf/2507.2216…

Programmable Data Planes for Network Security
The emergence of programmable data planes, and particularly switches supporting the P4 language, has transformed network security by enabling customized, line-rate packet processing. These switches, originally intended for flexible forwarding, now play a broader role: detecting and mitigating attacks such as DDoS and spoofing, enforcing next-generation firewall policies, and even supporting in-network cryptography and machine learning. These capabilities are made possible by techniques such as …

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
Ramy ElMallah, Krish Chhajer, Chi-Guhn Lee
https://arxiv.org/abs/2509.19524 https://

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
Robot learning papers typically report a single binary success rate (SR), which obscures where a policy succeeds or fails along a multi-step manipulation task. We argue that subgoal-level reporting should become routine: for each trajectory, a vector of per-subgoal SRs that makes partial competence visible (e.g., grasp vs. pour). We propose a blueprint for StepEval, a cost-aware plug-in evaluation framework that utilizes vision-language models (VLMs) as automated judges of subgoal outcomes from…

Neural network ensemble for computing cross sections for rotational transitions in H$_{2}$O H$_{2}$O collisions
Bikramaditya Mandal, Dmitri Babikov, Phillip C. Stancil, Robert C. Forrey, Roman V. Krems, Naduvalath Balakrishnan
https://arxiv.org/abs/2507.18974

Neural network ensemble for computing cross sections for rotational transitions in H$_{2}$O + H$_{2}$O collisions
Water (H$_2$O) is one of the most abundant molecules in the universe and is found in a wide variety of astrophysical environments. Rotational transitions in H$_2$O + H$_2$O collisions are important in modeling environments rich in water molecules but they are computationally intractable using quantum mechanical methods. Here, we present a machine learning (ML) tool using an ensemble of neural networks (NNs) to predict cross sections to construct a database of rate coefficients for rotationally …

On the Rate of Gaussian Approximation for Linear Regression Problems
Marat Khusainov, Marina Sheshukova, Alain Durmus, Sergey Samsonov
https://arxiv.org/abs/2509.14039 https://

On the Rate of Gaussian Approximation for Linear Regression Problems
In this paper, we consider the problem of Gaussian approximation for the online linear regression task. We derive the corresponding rates for the setting of a constant learning rate and study the explicit dependence of the convergence rate upon the problem dimension $d$ and quantities related to the design matrix. When the number of iterations $n$ is known in advance, our results yield the rate of normal approximation of order $\sqrt{\log{n}/n}$, provided that the sample size $n$ is large enoug…

Explainable Learning Rate Regimes for Stochastic Optimization
Zhuang Yang
https://arxiv.org/abs/2508.13639 https://arxiv.org/pdf/2508.13639

Explainable Learning Rate Regimes for Stochastic Optimization
Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one or more additional hyper-parameters manually whose bottlenecks include huge computational expenditure, time and power in practice. This work, in a natural and direct manner, clarifies how LR should be updated automatically only according to the intrinsic varia…

Semiparametric Learning of Integral Functionals on Submanifolds
Xiaohong Chen, Wayne Yuan Gao
https://arxiv.org/abs/2507.12673 https://

Semiparametric Learning of Integral Functionals on Submanifolds
This paper studies the semiparametric estimation and inference of integral functionals on submanifolds, which arise naturally in a variety of econometric settings. For linear integral functionals on a regular submanifold, we show that the semiparametric plug-in estimator attains the minimax-optimal convergence rate $n^{-\frac{s}{2s+d-m}}$, where $s$ is the Hölder smoothness order of the underlying nonparametric function, $d$ is the dimension of the first-stage nonparametric estimation, $m$ is …

Learning Rate Should Scale Inversely with High-Order Data Moments in High-Dimensional Online Independent Component Analysis
M. Oguzhan Gultekin, Samet Demir, Zafer Dogan
https://arxiv.org/abs/2509.15127

Learning Rate Should Scale Inversely with High-Order Data Moments in High-Dimensional Online Independent Component Analysis
We investigate the impact of high-order moments on the learning dynamics of an online Independent Component Analysis (ICA) algorithm under a high-dimensional data model composed of a weighted sum of two non-Gaussian random variables. This model allows precise control of the input moment structure via a weighting parameter. Building on an existing ordinary differential equation (ODE)-based analysis in the high-dimensional limit, we demonstrate that as the high-order moments increase, the algorit…

Multi-beam Beamforming in RIS-aided MIMO Subject to Reradiation Mask Constraints -- Optimization and Machine Learning Design
Shumin Wang, Hajar El Hassani, Marco Di Renzo, Marios Poulakis
https://arxiv.org/abs/2507.15367

Multi-beam Beamforming in RIS-aided MIMO Subject to Reradiation Mask Constraints -- Optimization and Machine Learning Design
Reconfigurable intelligent surfaces (RISs) are an emerging technology for improving spectral efficiency and reducing power consumption in future wireless systems. This paper investigates the joint design of the transmit precoding matrices and the RIS phase shift vector in a multi-user RIS-aided multiple-input multiple-output (MIMO) communication system. We formulate a max-min optimization problem to maximize the minimum achievable rate while considering transmit power and reradiation mask const…

Improving accuracy in short mortality rate series: Exploring Multi-step Forecasting Approaches in Hybrid Systems
Filipe C. L. Duarte, Paulo S. G. de Mattos Neto, Paulo R. A. Firmino
https://arxiv.org/abs/2509.22395

Improving accuracy in short mortality rate series: Exploring Multi-step Forecasting Approaches in Hybrid Systems
The decline in interest rates and economic stabilization has heightened the importance of accurate mortality rate forecasting, particularly in insurance and pension markets. Multi-step-ahead predictions are crucial for public health, demographic planning, and insurance risk assessments; however, they face challenges when data are limited. Hybrid systems that combine statistical and Machine Learning (ML) models offer a promising solution for handling both linear and nonlinear patterns. This stud…

Rapid Adaptation of SpO2 Estimation to Wearable Devices via Transfer Learning on Low-Sampling-Rate PPG
Zequan Liang, Ruoyu Zhang, Wei Shao, krishna Karthik, Ehsan Kourkchi, Setareh Rafatirad, Houman Homayoun
https://arxiv.org/abs/2509.12515

Rapid Adaptation of SpO2 Estimation to Wearable Devices via Transfer Learning on Low-Sampling-Rate PPG
Blood oxygen saturation (SpO2) is a vital marker for healthcare monitoring. Traditional SpO2 estimation methods often rely on complex clinical calibration, making them unsuitable for low-power, wearable applications. In this paper, we propose a transfer learning-based framework for the rapid adaptation of SpO2 estimation to energy-efficient wearable devices using low-sampling-rate (25Hz) dual-channel photoplethysmography (PPG). We first pretrain a bidirectional Long Short-Term Memory (BiLSTM) m…

LLM Meets the Sky: Heuristic Multi-Agent Reinforcement Learning for Secure Heterogeneous UAV Networks
Lijie Zheng, Ji He, Shih Yu Chang, Yulong Shen, Dusit Niyato
https://arxiv.org/abs/2507.17188

LLM Meets the Sky: Heuristic Multi-Agent Reinforcement Learning for Secure Heterogeneous UAV Networks
This work tackles the physical layer security (PLS) problem of maximizing the secrecy rate in heterogeneous UAV networks (HetUAVNs) under propulsion energy constraints. Unlike prior studies that assume uniform UAV capabilities or overlook energy-security trade-offs, we consider a realistic scenario where UAVs with diverse payloads and computation resources collaborate to serve ground terminals in the presence of eavesdroppers. To manage the complex coupling between UAV motion and communication,…

Leveraging Bi-Directional Channel Reciprocity for Robust Ultra-Low-Rate Implicit CSI Feedback with Deep Learning
Zhenyu Liu, Yi Ma, Rahim Tafazolli, Zhi Ding
https://arxiv.org/abs/2507.12301

Leveraging Bi-Directional Channel Reciprocity for Robust Ultra-Low-Rate Implicit CSI Feedback with Deep Learning
Deep learning-based implicit channel state information (CSI) feedback has been introduced to enhance spectral efficiency in massive MIMO systems. Existing methods often show performance degradation in ultra-low-rate scenarios and inadaptability across diverse environments. In this paper, we propose Dual-ImRUNet, an efficient uplink-assisted deep implicit CSI feedback framework incorporating two novel plug-in preprocessing modules to achieve ultra-low feedback rates while maintaining high enviro…

Global properties of the energy landscape: a testing and training arena for machine learned potentials
Vlad C\u{a}rare, Fabian L. Thiemann, Joe Morrow, David J. Wales, Edward O. Pyzer-Knapp, Luke Dicks
https://arxiv.org/abs/2508.16425

Global properties of the energy landscape: a testing and training arena for machine learned potentials
Machine learning interatomic potentials (MLIPs) have achieved remarkable accuracy on standard benchmarks, yet their ability to reproduce molecular kinetics -- critical for reaction rate calculations -- remains largely unexplored. We introduce Landscape17, a dataset of complete kinetic transition networks (KTNs) for the molecules of the MD17 dataset, computed using hybrid-level density functional theory. Each KTN contains minima, transition states, and approximate steepest-descent paths, along w…

Optimal Calibrated Signaling in Digital Auctions
Zhicheng Du, Wei Tang, Zihe Wang, Shuo Zhang
https://arxiv.org/abs/2507.17187 https://arxiv.org/pdf/2507.1…

Optimal Calibrated Signaling in Digital Auctions
In digital advertising, online platforms allocate ad impressions through real-time auctions, where advertisers typically rely on autobidding agents to optimize bids on their behalf. Unlike traditional auctions for physical goods, the value of an ad impression is uncertain and depends on the unknown click-through rate (CTR). While platforms can estimate CTRs more accurately using proprietary machine learning algorithms, these estimates/algorithms remain opaque to advertisers. This information as…

Biologically Plausible Online Hebbian Meta-Learning: Two-Timescale Local Rules for Spiking Neural Brain Interfaces
Sriram V. C. Nallani, Gautham Ramachandran, Sahil S. Shah
https://arxiv.org/abs/2509.14447

Biologically Plausible Online Hebbian Meta-Learning: Two-Timescale Local Rules for Spiking Neural Brain Interfaces
Brain-Computer Interfaces face challenges from neural signal instability and memory constraints for real-time implantable applications. We introduce an online SNN decoder using local three-factor learning rules with dual-timescale eligibility traces that avoid backpropagation through time while maintaining competitive performance. Our approach combines error-modulated Hebbian updates, fast/slow trace consolidation, and adaptive learning rate control, requiring only O(1) memory versus O(T) for B…

On the distance between mean and geometric median in high dimensions
Richard Schwank, Mathias Drton
https://arxiv.org/abs/2508.12926 https://arxiv.org/pdf/…

On the distance between mean and geometric median in high dimensions
The geometric median, a notion of center for multivariate distributions, has gained recent attention in robust statistics and machine learning. Although conceptually distinct from the mean (i.e., expectation), we demonstrate that both are very close in high dimensions when the dependence between the distribution components is suitably controlled. Concretely, we find an upper bound on the distance that vanishes with the dimension asymptotically, and derive a rate-matching first order expansion o…

Group Relative Policy Optimization for Text-to-Speech with Large Language Models
Chang Liu, Ya-Jun Hu, Ying-Ying Gao, Shi-Lei Zhang, Zhen-Hua Ling
https://arxiv.org/abs/2509.18798

Group Relative Policy Optimization for Text-to-Speech with Large Language Models
This paper proposes a GRPO-based approach to enhance the performance of large language model (LLM)-based text-to-speech (TTS) models by deriving rewards from an off-the-shelf automatic speech recognition (ASR) model. Compared to previous reinforcement learning methods for LLM-based TTS, our method requires no dedicated model for reward computation or training. Moreover, we design a composite reward function that combines character error rate (CER) with negative log-likelihood (NLL) obtained fro…

Energy-Efficient RSMA-enabled Low-altitude MEC Optimization Via Generative AI-enhanced Deep Reinforcement Learning
Xudong Wang, Hongyang Du, Lei Feng, Kaibin Huang
https://arxiv.org/abs/2507.12910

Energy-Efficient RSMA-enabled Low-altitude MEC Optimization Via Generative AI-enhanced Deep Reinforcement Learning
The growing demand for low-latency computing in 6G is driving the use of UAV-based low-altitude mobile edge computing (MEC) systems. However, limited spectrum often leads to severe uplink interference among ground terminals (GTs). In this paper, we investigate a rate-splitting multiple access (RSMA)-enabled low-altitude MEC system, where a UAV-based edge server assists multiple GTs in concurrently offloading their tasks over a shared uplink. We formulate a joint optimization problem involving t…

Effective continuous equations for adaptive SGD: a stochastic analysis view
Luca Callisti, Marco Romito, Francesco Triggiano
https://arxiv.org/abs/2509.21614 https://

Effective continuous equations for adaptive SGD: a stochastic analysis view
We present a theoretical analysis of some popular adaptive Stochastic Gradient Descent (SGD) methods in the small learning rate regime. Using the stochastic modified equations framework introduced by Li et al., we derive effective continuous stochastic dynamics for these methods. Our key contribution is that sampling-induced noise in SGD manifests in the limit as independent Brownian motions driving the parameter and gradient second momentum evolutions. Furthermore, extending the approach of Ma…

BEAM-Net: A Deep Learning Framework with Bone Enhancement Attention Mechanism for High Resolution High Frame Rate Ultrasound Beamforming
Midhila Madhusoodanan, Mahesh Raveendranatha Panicker, Pisharody Harikrishnan Gopalakrishnan, Abhilash Rakkunedeth Hareendranathan
https://arxiv.org/abs/2507.15306

BEAM-Net: A Deep Learning Framework with Bone Enhancement Attention Mechanism for High Resolution High Frame Rate Ultrasound Beamforming
Pocket-sized, low-cost point-of-care ultrasound (POCUS) devices are increasingly used in musculoskeletal (MSK) applications for structural examination of bone tissue. However, the image quality in MSK ultrasound is often limited by speckle noise, low resolution, poor contrast, and anisotropic reflections, making bone images difficult to interpret without additional post-processing. Typically, medical ultrasound systems use delay and sum beamforming (DASB) for image reconstruction, which is not …

Dataset Distillation as Data Compression: A Rate-Utility Perspective
Youneng Bao, Yiping Liu, Zhuo Chen, Yongsheng Liang, Mu Li, Kede Ma
https://arxiv.org/abs/2507.17221

Dataset Distillation as Data Compression: A Rate-Utility Perspective
Driven by the ``scale-is-everything'' paradigm, modern machine learning increasingly demands ever-larger datasets and models, yielding prohibitive computational and storage requirements. Dataset distillation mitigates this by compressing an original dataset into a small set of synthetic samples, while preserving its full utility. Yet, existing methods either maximize performance under fixed storage budgets or pursue suitable synthetic data representations for redundancy removal, without jointly…

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
Bingrui Li, Jiaxin Wen, Zhanpeng Zhou, Jun Zhu, Jianfei Chen
https://arxiv.org/abs/2509.25049 https://…

Efficient Hyperparameter Tuning via Trajectory Invariance Principle
As hyperparameter tuning becomes increasingly costly at scale, efficient tuning methods are essential. Yet principles for guiding hyperparameter tuning remain limited. In this work, we seek to establish such principles by considering a broad range of hyperparameters, including batch size, learning rate, and weight decay. We identify a phenomenon we call trajectory invariance, where pre-training loss curves, gradient noise, and gradient norm exhibit invariance--closely overlapping--with respect …

The Information Dynamics of Generative Diffusion
Luca Ambrogioni
https://arxiv.org/abs/2508.19897 https://arxiv.org/pdf/2508.19897

The Information Dynamics of Generative Diffusion
Generative diffusion models have emerged as a powerful class of models in machine learning, yet a unified theoretical understanding of their operation is still developing. This perspective paper provides an integrated perspective on generative diffusion by connecting their dynamic, information-theoretic, and thermodynamic properties under a unified mathematical framework. We demonstrate that the rate of conditional entropy production during generation (i.e. the generative bandwidth) is directly…

DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
Xianbiao Qi, Marco Chen, Wenjie Xiao, Jiaquan Ye, Yelin He, Chun-Guang Li, Zhouchen Lin
https://arxiv.org/abs/2507.17501

DNT: a Deeply Normalized Transformer that can be trained by Momentum SGD
Transformers have become the de facto backbone of modern deep learning, yet their training typically demands an advanced optimizer with adaptive learning rate like AdamW, rather than a momentum SGDW (mSGDW). Previous works show that it is mainly due to a heavy-tailed distribution of the gradients. In this paper, we introduce a Deeply Normalized Transformer (DNT), which is meticulously engineered to overcome this limitation enabling seamless training with vanilla mSGDW while yielding comparable …

A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff
J\'er\^ome Emery, Ali Hasanzadeh Karkan, Jean-Fran\c{c}ois Frigon, Fran\c{c}ois Leduc-Primeau
https://arxiv.org/abs/2507.18587

A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff
Deep learning (DL) has emerged as a solution for precoding in massive multiple-input multiple-output (mMIMO) systems due to its capacity to learn the characteristics of the propagation environment. However, training such a model requires high-quality, local datasets at the deployment site, which are often difficult to collect. We propose a transformer-based foundation model for mMIMO precoding that seeks to minimize the energy consumption of the transmitter while dynamically adapting to per-use…

AI-Powered Machine Learning Approaches for Fault Diagnosis in Industrial Pumps
Khaled M. A. Alghtus, Ayad Gannan, Khalid M. Alhajri, Ali L. A. Al Jubouri, Hassan A. I. Al-Janahi
https://arxiv.org/abs/2508.15550

AI-Powered Machine Learning Approaches for Fault Diagnosis in Industrial Pumps
This study presents a practical approach for early fault detection in industrial pump systems using real-world sensor data from a large-scale vertical centrifugal pump operating in a demanding marine environment. Five key operational parameters were monitored: vibration, temperature, flow rate, pressure, and electrical current. A dual-threshold labeling method was applied, combining fixed engineering limits with adaptive thresholds calculated as the 95th percentile of historical sensor values. …

State-of-the-Art Dysarthric Speech Recognition with MetaICL for on-the-fly Personalization
Dhruuv Agarwal, Harry Zhang, Yang Yu, Quan Wang
https://arxiv.org/abs/2509.15516 https…

State-of-the-Art Dysarthric Speech Recognition with MetaICL for on-the-fly Personalization
Personalizing Automatic Speech Recognition (ASR) for dysarthric speech is crucial but challenging due to training and storing of individual user adapters. We propose a hybrid meta-training method for a single model, excelling in zero-shot and few-shot on-the-fly personalization via in-context learning (ICL). Measuring Word Error Rate (WER) on state-of-the-art subsets, the model achieves 13.9% WER on Euphonia which surpasses speaker-independent baselines (17.5% WER) and rivals user-specific pers…

Scaling with Collapse: Efficient and Predictable Training of LLM Families
Shane Bergsma, Bin Claire Zhang, Nolan Dey, Shaheer Muhammad, Gurpreet Gosal, Joel Hestness
https://arxiv.org/abs/2509.25087

Scaling with Collapse: Efficient and Predictable Training of LLM Families
Effective LLM training relies on *consistency*, meaning that key quantities -- such as final losses and optimal hyperparameters -- scale predictably across model sizes. Qiu et al. (2025) recently showed that this consistency extends beyond scalars: whole training loss curves can *collapse* onto a universal trajectory after a simple normalization. What remains unclear is whether this phenomenon holds for LLM families trained under *practical scaling recipes*, where width, depth, learning rate, b…

Data-Driven Reconstruction of Significant Wave Heights from Sparse Observations
Hongyuan Shi, Yilin Zhai, Ping Dong, Zaijin You, Chao Zhan, Qing Wang
https://arxiv.org/abs/2509.19384

Data-Driven Reconstruction of Significant Wave Heights from Sparse Observations
Reconstructing high-resolution regional significant wave height fields from sparse and uneven buoy observations remains a core challenge for ocean monitoring and risk-aware operations. We introduce AUWave, a hybrid deep learning framework that fuses a station-wise sequence encoder (MLP) with a multi-scale U-Net enhanced by a bottleneck self-attention layer to recover 32$\times$32 regional SWH fields. A systematic Bayesian hyperparameter search with Optuna identifies the learning rate as the dom…

DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
Yuen Chen, Yian Wang, Hari Sundaram
https://arxiv.org/abs/2509.16173 https://

DIVEBATCH: Accelerating Model Training Through Gradient-Diversity Aware Batch Size Adaptation
The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally expensive. Stochastic gradient descent (SGD) and its variants are widely used to train deep neural networks. In contrast to traditional approaches that focus on tuning the learning rate, we propose a novel adaptive batch size SGD algorithm, DiveBatch, that dynamically adjusts the batch size. Adapting the batch size is c…

Towards Automated EEG-Based Detection Using Deep Convolutional Autoencoders
Annika Stiehl, Nicolas Weeger, Christian Uhl, Dominic Bechtold, Nicole Ille, Stefan Gei{\ss}els\"oder
https://arxiv.org/abs/2508.20535

Towards Automated EEG-Based Detection Using Deep Convolutional Autoencoders
Epilepsy is one of the most common neurological disorders. This disease requires reliable and efficient seizure detection methods. Electroencephalography (EEG) is the gold standard for seizure monitoring, but its manual analysis is a time-consuming task that requires expert knowledge. In addition, there are no well-defined features that allow fully automated analysis. Existing deep learning-based approaches struggle to achieve high sensitivity while maintaining a low false alarm rate per hour (…

Physics-Informed Linear Model (PILM): Analytical Representations and Application to Crustal Strain Rate Estimation
Tomohisa Okazaki
https://arxiv.org/abs/2507.12218

Physics-Informed Linear Model (PILM): Analytical Representations and Application to Crustal Strain Rate Estimation
Many physical systems are described by partial differential equations (PDEs), and solving these equations and estimating their coefficients or boundary conditions (BCs) from observational data play a crucial role in understanding the associated phenomena. Recently, a machine learning approach known as physics-informed neural network, which solves PDEs using neural networks by minimizing the sum of residuals from the PDEs, BCs, and data, has gained significant attention in the scientific communi…

Targeted Fine-Tuning of DNN-Based Receivers via Influence Functions
Marko Tuononen, Heikki Penttinen, Ville Hautam\"aki
https://arxiv.org/abs/2509.15950 https://

Targeted Fine-Tuning of DNN-Based Receivers via Influence Functions
We present the first use of influence functions for deep learning-based wireless receivers. Applied to DeepRx, a fully convolutional receiver, influence analysis reveals which training samples drive bit predictions, enabling targeted fine-tuning of poorly performing cases. We show that loss-relative influence with capacity-like binary cross-entropy loss and first-order updates on beneficial samples most consistently improves bit error rate toward genie-aided performance, outperforming random fi…

Efficient Quantization-Aware Neural Receivers: Beyond Post-Training Quantization
SaiKrishna Saketh Yellapragada, Esa Ollila, Mario Costa
https://arxiv.org/abs/2509.13786 https:/…

Efficient Quantization-Aware Neural Receivers: Beyond Post-Training Quantization
As wireless communication systems advance toward Sixth Generation (6G) Radio Access Networks (RAN), Deep Learning (DL)-based neural receivers are emerging as transformative solutions for Physical Layer (PHY) processing, delivering superior Block Error Rate (BLER) performance compared to traditional model-based approaches. Practical deployment on resource-constrained hardware, however, requires efficient quantization to reduce latency, energy, and memory without sacrificing reliability. We exten…