Tootfinder

This https://arxiv.org/abs/2309.10716 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racing
This work presents a novel Learning Model Predictive Control (LMPC) strategy for autonomous racing at the handling limit that can iteratively explore and learn unknown dynamics in high-speed operational domains. We start from existing LMPC formulations and modify the system dynamics learning method. In particular, our approach uses a nominal, global, nonlinear, physics-based model with a local, linear, data-driven learning of the error dynamics. We conducted experiments in simulation and on 1/1…

This https://arxiv.org/abs/2302.13837 has been replaced.
link: https://scholar.google.com/scholar?q=a

Decentralized Learning Made Practical with Client Sampling
Decentralized learning (DL) leverages edge devices for collaborative model training while avoiding coordination by a central server. Due to privacy concerns, DL has become an attractive alternative to centralized learning schemes since training data never leaves the device. In a round of DL, all nodes participate in model training and exchange their model with some other nodes. Performing DL in large-scale heterogeneous networks results in high communication costs and prolonged round durations …

This https://arxiv.org/abs/2312.11126 has been replaced.
link: https://scholar.google.com/scholar?q=a

Harnessing Inherent Noises for Privacy Preservation in Quantum Machine Learning
Quantum computing revolutionizes the way of solving complex problems and handling vast datasets, which shows great potential to accelerate the machine learning process. However, data leakage in quantum machine learning (QML) may present privacy risks. Although differential privacy (DP), which protects privacy through the injection of artificial noise, is a well-established approach, its application in the QML domain remains under-explored. In this paper, we propose to harness inherent quantum n…

This https://arxiv.org/abs/2403.01517 has been replaced.
link: https://scholar.google.com/scholar?q=a

MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images
Recent learning methods for object pose estimation require resource-intensive training for each individual object instance or category, hampering their scalability in real applications when confronted with previously unseen objects. In this paper, we propose MatchU, a Fuse-Describe-Match strategy for 6D pose estimation from RGB-D images. MatchU is a generic approach that fuses 2D texture and 3D geometric cues for 6D pose prediction of unseen objects. We rely on learning geometric 3D descriptors…

This https://arxiv.org/abs/2201.09754 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Reinforcement Learning with Spiking Q-learning
With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Most of them either lack generalization ability or employ Artificial Neural Networks (ANNs) to estimate value function in training. The former n…

This https://arxiv.org/abs/2001.03048 has been replaced.
link: https://scholar.google.com/scholar?q=a

Resource-Efficient Neural Networks for Embedded Systems
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning tec…

Q-learning in Dynamic Treatment Regimes with Misclassified Binary Outcome
Dan Liu, Wenqing He
https://arxiv.org/abs/2404.04697 https://

Q-learning in Dynamic Treatment Regimes with Misclassified Binary Outcome
The study of precision medicine involves dynamic treatment regimes (DTRs), which are sequences of treatment decision rules recommended by taking patient-level information as input. The primary goal of the DTR study is to identify an optimal DTR, a sequence of treatment decision rules that leads to the best expected clinical outcome. Statistical methods have been developed in recent years to estimate an optimal DTR, including Q-learning, a regression-based method in the DTR literature. Although …

Deep Reinforcement Learning Control for Disturbance Rejection in a Nonlinear Dynamic System with Parametric Uncertainty
Vincent W. Hill
https://arxiv.org/abs/2404.04699

Deep Reinforcement Learning Control for Disturbance Rejection in a Nonlinear Dynamic System with Parametric Uncertainty
This work describes a technique for active rejection of multiple independent and time-correlated stochastic disturbances for a nonlinear flexible inverted pendulum with cart system with uncertain model parameters. The control law is determined through deep reinforcement learning, specifically with a continuous actor-critic variant of deep Q-learning known as Deep Deterministic Policy Gradient, while the disturbance magnitudes evolve via independent stochastic processes. Simulation results are t…

This https://arxiv.org/abs/2403.00987 has been replaced.
link: https://scholar.google.com/scholar?q=a

Composite Distributed Learning and Synchronization of Nonlinear Multi-Agent Systems with Complete Uncertain Dynamics
This paper addresses the problem of composite synchronization and learning control in a network of multi-agent robotic manipulator systems with heterogeneous nonlinear uncertainties under a leader-follower framework. A novel two-layer distributed adaptive learning control strategy is introduced, comprising a first-layer distributed cooperative estimator and a second-layer decentralized deterministic learning controller. The first layer is to facilitate each robotic agent's estimation of the lea…

This https://arxiv.org/abs/2404.01054 has been replaced.
link: https://scholar.google.com/scholar?q=a

Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment
Best-of-N (BoN) sampling with a reward model has been shown to be an effective strategy for aligning Large Language Models (LLMs) to human preferences at the time of decoding. BoN sampling is susceptible to a problem known as reward hacking. Because the reward model is an imperfect proxy for the true objective, over-optimizing its value can compromise its performance on the true objective. A common solution to prevent reward hacking in preference learning techniques is to optimize a reward usin…

This https://arxiv.org/abs/2402.19212 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…

Deep Reinforcement Learning: A Convex Optimization Approach
In this paper, we consider reinforcement learning of nonlinear systems with continuous state and action spaces. We present an episodic learning algorithm, where we for each episode use convex optimization to find a two-layer neural network approximation of the optimal $Q$-function. The convex optimization approach guarantees that the weights calculated at each episode are optimal, with respect to the given sampled states and actions of the current episode. For stable nonlinear systems, we show …

This https://arxiv.org/abs/2309.10716 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racing
This work presents a novel Learning Model Predictive Control (LMPC) strategy for autonomous racing at the handling limit that can iteratively explore and learn unknown dynamics in high-speed operational domains. We start from existing LMPC formulations and modify the system dynamics learning method. In particular, our approach uses a nominal, global, nonlinear, physics-based model with a local, linear, data-driven learning of the error dynamics. We conducted experiments in simulation and on 1/1…

This https://arxiv.org/abs/2404.00076 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks
Audio-based machine learning systems frequently use public or third-party data, which might be inaccurate. This exposes deep neural network (DNN) models trained on such data to potential data poisoning attacks. In this type of assault, attackers can train the DNN model using poisoned data, potentially degrading its performance. Another type of data poisoning attack that is extremely relevant to our investigation is label flipping, in which the attacker manipulates the labels for a subset of dat…

This https://arxiv.org/abs/2209.14399 has been replaced.
link: https://scholar.google.com/scholar?q=a

FIRE: A Failure-Adaptive Reinforcement Learning Framework for Edge Computing Migrations
In edge computing, users' service profiles are migrated due to user mobility. Reinforcement learning (RL) frameworks have been proposed to do so, often trained on simulated data. However, existing RL frameworks overlook occasional server failures, which although rare, impact latency-sensitive applications like autonomous driving and real-time obstacle detection. Nevertheless, these failures (rare events), being not adequately represented in historical training data, pose a challenge for data-dr…

This https://arxiv.org/abs/2209.14089 has been replaced.
link: https://scholar.google.com/scholar?q=a

Combining Reinforcement Learning and Tensor Networks, with an Application to Dynamical Large Deviations
We present a framework to integrate tensor network (TN) methods with reinforcement learning (RL) for solving dynamical optimisation tasks. We consider the RL actor-critic method, a model-free approach for solving RL problems, and introduce TNs as the approximators for its policy and value functions. Our "actor-critic with tensor networks" (ACTeN) method is especially well suited to problems with large and factorisable state and action spaces. As an illustration of the applicability of ACTeN we …

This https://arxiv.org/abs/2404.15786 has been replaced.
link: https://scholar.google.com/scholar?q=a

Rethinking Model Prototyping through the MedMNIST+ Dataset Collection
The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, prioritization of marginal performance improvements on a few, narrowly scoped benchmarks over clinical applicability has slowed down meaningful algorithmic progress. This trend often results in excessive fine-tuning of existing methods to achieve state-of-the-art performance on selected datasets rather than fostering clinically rel…

This https://arxiv.org/abs/2401.15541 has been replaced.
link: https://scholar.google.com/scholar?q=a

Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learning
In the ambitious realm of space AI, the integration of federated learning (FL) with low Earth orbit (LEO) satellite constellations holds immense promise. However, many challenges persist in terms of feasibility, learning efficiency, and convergence. These hurdles stem from the bottleneck in communication, characterized by sporadic and irregular connectivity between LEO satellites and ground stations, coupled with the limited computation capability of satellite edge computing (SEC). This paper p…

This https://arxiv.org/abs/2403.08411 has been replaced.
link: https://scholar.google.com/scholar?q=a

Robust Distributed Compression with Learned Heegard-Berger Scheme
We consider lossy compression of an information source when decoder-only side information may be absent. This setup, also referred to as the Heegard-Berger or Kaspi problem, is a special case of robust distributed source coding. Building upon previous works on neural network-based distributed compressors developed for the decoder-only side information (Wyner-Ziv) case, we propose learning-based schemes that are amenable to the availability of side information. We find that our learned compresso…

This https://arxiv.org/abs/2012.10142 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning and balancing unknown loads in large-scale systems
Consider a system of identical server pools where tasks with exponentially distributed service times arrive as a time-inhomogenenous Poisson process. An admission threshold is used in an inner control loop to assign incoming tasks to server pools while, in an outer control loop, a learning scheme adjusts this threshold over time to keep it aligned with the unknown offered load of the system. In a many-server regime, we prove that the learning scheme reaches an equilibrium along intervals of tim…

This https://arxiv.org/abs/2212.06166 has been replaced.
link: https://scholar.google.com/scholar?q=a

Rapid determination of LISA sensitivity to extreme mass ratio inspirals with machine learning
Gravitational wave observations of the inspiral of stellar-mass compact objects into massive black holes (MBHs), extreme mass ratio inspirals (EMRIs), enable precision measurements of parameters such as the MBH mass and spin. The Laser Interferometer Space Antenna is expected to detect sufficient EMRIs to probe the underlying source population, testing theories of the formation and evolution of MBHs and their environments. Population studies are subject to selection effects that vary across the…

This https://arxiv.org/abs/2307.04384 has been replaced.
link: https://scholar.google.com/scholar?q=a

Neural Causal Graph Collaborative Filtering
Graph collaborative filtering (GCF) has gained considerable attention in recommendation systems by leveraging graph learning techniques to enhance collaborative filtering (CF). One classical approach in GCF is to learn user and item embeddings with Graph Convolutional Network (GCN) and utilize these embeddings for CF models. However, existing GCN-based methods are insufficient in generating satisfactory embeddings for CF models. This is because they fail to model complex node dependencies and v…

This https://arxiv.org/abs/2005.07842 has been replaced.
link: https://scholar.google.com/scholar?q=a

DEFM: Delay E mbedding based Forecast Machine for Time Series Forecasting by Spatiotemporal Information Transformation
Making accurate forecasts for a complex system is a challenge in various practical applications. The major difficulty in solving such a problem concerns nonlinear spatiotemporal dynamics with time-varying characteristics. Takens' delay embedding theory provides a way to transform high-dimensional spatial information into temporal information. In this work, by combining delay embedding theory and deep learning techniques, we propose a novel framework, Delay-Embedding-based Forecast Machine (DEFM…

This https://arxiv.org/abs/2403.00764 has been replaced.
link: https://scholar.google.com/scholar?q=a

Optical-coherence-tomography-based deep-learning scatterer-density estimator using physically accurate noise model
We demonstrate a deep-learning-based scatterer density estimator (SDE) that processes local speckle patterns of optical coherence tomography (OCT) images and estimates the scatterer density behind each speckle pattern. The SDE is trained using large quantities of numerically simulated OCT images and their associated scatterer densities. The numerical simulation uses a noise model that incorporates the spatial properties of three types of noise, i.e., shot noise, relative-intensity noise, and no…

This https://arxiv.org/abs/2109.01002 has been replaced.
link: https://scholar.google.com/scholar?q=a

DocTer: Documentation Guided Fuzzing for Testing Deep Learning API Functions
Input constraints are useful for many software development tasks. For example, input constraints of a function enable the generation of valid inputs, i.e., inputs that follow these constraints, to test the function deeper. API functions of deep learning (DL) libraries have DL specific input constraints, which are described informally in the free form API documentation. Existing constraint extraction techniques are ineffective for extracting DL specific input constraints. To fill this gap, we …

This https://arxiv.org/abs/2404.00686 has been replaced.
link: https://scholar.google.com/scholar?q=a

Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning
Accounting for the uncertainty of value functions boosts exploration in Reinforcement Learning (RL). Our work introduces Maximum Mean Discrepancy Q-Learning (MMD-QL) to improve Wasserstein Q-Learning (WQL) for uncertainty propagation during Temporal Difference (TD) updates. MMD-QL uses the MMD barycenter for this purpose, as MMD provides a tighter estimate of closeness between probability measures than the Wasserstein distance. Firstly, we establish that MMD-QL is Probably Approximately Correct…

Dynamic Treatment Regimes with Replicated Observations Available for Error-prone Covariates: a Q-learning Approach
Dan Liu, Wenqing He
https://arxiv.org/abs/2404.04696

Dynamic Treatment Regimes with Replicated Observations Available for Error-prone Covariates: a Q-learning Approach
Dynamic treatment regimes (DTRs) have received an increasing interest in recent years. DTRs are sequences of treatment decision rules tailored to patient-level information. The main goal of the DTR study is to identify an optimal DTR, a sequence of treatment decision rules that yields the best expected clinical outcome. Q-learning has been considered as one of the most popular regression-based methods to estimate the optimal DTR. However, it is rarely studied in an error-prone setting, where th…

This https://arxiv.org/abs/2211.13513 has been replaced.
link: https://scholar.google.com/scholar?q=a

Waterproof: Educational Software for Learning How to Write Mathematical Proofs
In order to help students learn how to write mathematical proofs, we adapt the Coq proof assistant into an educational tool we call Waterproof. Like with other interactive theorem provers, students write out their proofs inside the software using a specific syntax, and the software provides feedback on the logical validity of each step. Waterproof consists of two components: a custom proof language that allows formal, machine-verified proofs to be written in a style that closely resembles handw…

This https://arxiv.org/abs/2402.04342 has been replaced.
link: https://scholar.google.com/scholar?q=a

Building Ocean Climate Emulators
The current explosion in machine learning for climate has led to skilled, computationally cheap emulators for the atmosphere. However, the research for ocean emulators remains nascent despite the large potential for accelerating coupled climate simulations and improving ocean forecasts on all timescales. There are several fundamental questions to address that can facilitate the creation of ocean emulators. Here we focus on two questions: 1) the role of the atmosphere in improving the extended s…

This https://arxiv.org/abs/2312.13286 has been replaced.
link: https://scholar.google.com/scholar?q=a

Generative Multimodal Models are In-Context Learners
The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-context learning capabilities of large multimodal models can be significantly enhanced by effective scaling-up. We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences with a unified a…

This https://arxiv.org/abs/2312.15583 has been replaced.
link: https://scholar.google.com/scholar?q=a

ITEACNet: Inverted Teacher-studEnt seArch Conversation Network
Due to the widespread applications of conversations in human-computer interaction, Conversation Emotion Recognition (CER) has attracted increasing attention from researchers. In real-world scenarios, the emotional states of both participants in a conversation tend to maintain a relatively stable pattern within the local context, and often encountering issues with incomplete data patterns. Focusing on these two key challenges, we propose a novel framework for incomplete multimodal learning in CE…

This https://arxiv.org/abs/2307.08424 has been replaced.
link: https://scholar.google.com/scholar?q=a

Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model
Model inversion attacks (MIAs) aim to recover private data from inaccessible training sets of deep learning models, posing a privacy threat. MIAs primarily focus on the white-box scenario where attackers have full access to the model's structure and parameters. However, practical applications are usually in black-box scenarios or label-only scenarios, i.e., the attackers can only obtain the output confidence vectors or labels by accessing the model. Therefore, the attack models in existing MIAs…

This https://arxiv.org/abs/2309.05310 has been replaced.
link: https://scholar.google.com/scholar?q=a

ImitationNet: Unsupervised Human-to-Robot Motion Retargeting via Shared Latent Space
This paper introduces a novel deep-learning approach for human-to-robot motion retargeting, enabling robots to mimic human poses accurately. Contrary to prior deep-learning-based works, our method does not require paired human-to-robot data, which facilitates its translation to new robots. First, we construct a shared latent space between humans and robots via adaptive contrastive learning that takes advantage of a proposed cross-domain similarity metric between the human and robot poses. Addit…

LOQA: Learning with Opponent Q-Learning Awareness
Milad Aghajohari, Juan Agustin Duque, Tim Cooijmans, Aaron Courville
https://arxiv.org/abs/2405.01035 htt…

LOQA: Learning with Opponent Q-Learning Awareness
In various real-world scenarios, interactions among agents often resemble the dynamics of general-sum games, where each agent strives to optimize its own utility. Despite the ubiquitous relevance of such settings, decentralized machine learning algorithms have struggled to find equilibria that maximize individual utility while preserving social welfare. In this paper we introduce Learning with Opponent Q-Learning Awareness (LOQA), a novel, decentralized reinforcement learning algorithm tailored…

This https://arxiv.org/abs/1902.06931 has been replaced.
link: https://scholar.google.com/scholar?q=a

On the consistency of supervised learning with missing values
In many application settings, the data have missing entries which make analysis challenging. An abundant literature addresses missing values in an inferential framework: estimating parameters and their variance from incomplete tables. Here, we consider supervised-learning settings: predicting a target when missing values appear in both training and testing data. We show the consistency of two approaches in prediction. A striking result is that the widely-used method of imputing with a constant,…

This https://arxiv.org/abs/2401.03424 has been replaced.
link: https://scholar.google.com/scholar?q=a

MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition
While automatic speech recognition (ASR) systems degrade significantly in noisy environments, audio-visual speech recognition (AVSR) systems aim to complement the audio stream with noise-invariant visual cues and improve the system's robustness. However, current studies mainly focus on fusing the well-learned modality features, like the output of modality-specific encoders, without considering the contextual relationship during the modality feature learning. In this study, we propose a multi-la…

This https://arxiv.org/abs/2312.10561 has been replaced.
link: https://scholar.google.com/scholar?q=a

Enabling Accelerators for Graph Computing
The advent of Graph Neural Networks (GNNs) has revolutionized the field of machine learning, offering a novel paradigm for learning on graph-structured data. Unlike traditional neural networks, GNNs are capable of capturing complex relationships and dependencies inherent in graph data, making them particularly suited for a wide range of applications including social network analysis, molecular chemistry, and network security. GNNs, with their unique structure and operation, present new computat…

This https://arxiv.org/abs/2102.13273 has been replaced.
link: https://scholar.google.com/scholar?q=a

Application-Driven Learning: A Closed-Loop Prediction and Optimization Approach Applied to Dynamic Reserves and Demand Forecasting
Forecasting and decision-making are generally modeled as two sequential steps with no feedback, following an open-loop approach. In this paper, we present application-driven learning, a new closed-loop framework in which the processes of forecasting and decision-making are merged and co-optimized through a bilevel optimization problem. We present our methodology in a general format and prove that the solution converges to the best estimator in terms of the expected cost of the selected applicat…

This https://arxiv.org/abs/2111.05778 has been replaced.
link: https://scholar.google.com/scholar?q=a

Theoretical and Empirical Analysis of a Fast Algorithm for Extracting Polygons from Signed Distance Bounds
Recently there has been renewed interest in signed distance bound representations due to their unique properties for 3D shape modelling. This is especially the case for deep learning-based bounds. However, it is beneficial to work with polygons in most computer-graphics applications. Thus, in this paper we introduce and investigate an asymptotically fast method for transforming signed distance bounds into polygon meshes. This is achieved by combining the principles of sphere tracing (or ray mar…

This https://arxiv.org/abs/2109.14200 has been replaced.
link: https://scholar.google.com/scholar?q=a

Can phones, syllables, and words emerge as side-products of cross-situational audiovisual learning? -- A computational investigation
Decades of research has studied how language learning infants learn to discriminate speech sounds, segment words, and associate words with their meanings. While gradual development of such capabilities is unquestionable, the exact nature of these skills and the underlying mental representations yet remains unclear. In parallel, computational studies have shown that basic comprehension of speech can be achieved by statistical learning between speech and concurrent referentially ambiguous visual …

This https://arxiv.org/abs/2007.10609 has been replaced.
link: https://scholar.google.com/scholar?q=a

SUBPLEX: Towards a Better Understanding of Black Box Model Explanations at the Subpopulation Level
Understanding the interpretation of machine learning (ML) models has been of paramount importance when making decisions with societal impacts such as transport control, financial activities, and medical diagnosis. While current model interpretation methodologies focus on using locally linear functions to approximate the models or creating self-explanatory models that give explanations to each input instance, they do not focus on model interpretation at the subpopulation level, which is the unde…

This https://arxiv.org/abs/2402.03913 has been replaced.
link: https://scholar.google.com/scholar?q=a

Machine learning stochastic differential equations for the evolution of order parameters of classical many-body systems in and out of equilibrium
We develop a machine learning algorithm to infer the emergent stochastic equation governing the evolution of an order parameter of a many-body system. We train our neural network to independently learn the directed force acting on the order parameter as well as an effective diffusive noise. We illustrate our approach using the classical Ising model endowed with Glauber dynamics, and the contact process as test cases. For both models, which represent paradigmatic equilibrium and nonequilibrium s…

This https://arxiv.org/abs/2207.08993 has been replaced.
link: https://scholar.google.com/scholar?q=a

Machine Learning in Orbit Estimation: a Survey
Since the late 1950s, when the first artificial satellite was launched, the number of Resident Space Objects has steadily increased. It is estimated that around one million objects larger than one cm are currently orbiting the Earth, with only thirty thousand larger than ten cm being tracked. To avert a chain reaction of collisions, known as Kessler Syndrome, it is essential to accurately track and predict debris and satellites' orbits. Current approximate physics-based methods have errors in t…

This https://arxiv.org/abs/2402.04101 has been replaced.
link: https://scholar.google.com/scholar?q=a

VRMM: A Volumetric Relightable Morphable Head Model
In this paper, we introduce the Volumetric Relightable Morphable Model (VRMM), a novel volumetric and parametric facial prior for 3D face modeling. While recent volumetric prior models offer improvements over traditional methods like 3D Morphable Models (3DMMs), they face challenges in model learning and personalized reconstructions. Our VRMM overcomes these by employing a novel training framework that efficiently disentangles and encodes latent spaces of identity, expression, and lighting into…

Periodicity in Hedge-myopic system and an asymmetric NE-solving paradigm for two-player zero-sum games
Xinxiang Guo, Yifen Mu, Xiaoguang Yang
https://arxiv.org/abs/2403.04336

Periodicity in Hedge-myopic system and an asymmetric NE-solving paradigm for two-player zero-sum games
In this paper, we consider the $n \times n$ two-payer zero-sum repeated game in which one player (player X) employs the popular Hedge (also called multiplicative weights update) learning algorithm while the other player (player Y) adopts the myopic best response. We investigate the dynamics of such Hedge-myopic system by defining a metric $Q(\textbf{x}_t)$, which measures the distance between the stage strategy $\textbf{x}_t$ and Nash Equilibrium (NE) strategy of player X. We analyze the trend …

This https://arxiv.org/abs/2211.07125 has been replaced.
link: https://scholar.google.com/scholar?q=a

Global Performance Guarantees for Neural Network Models of AC Power Flow
Machine learning, which can generate extremely fast and highly accurate black-box surrogate models, is increasingly being applied to a variety of AC power flow problems. Rigorously verifying the accuracy of the resulting black-box models, however, is computationally challenging. This paper develops a tractable neural network verification procedure which incorporates the ground truth of the non-linear AC power flow equations to determine worst-case neural network prediction error. Our approach, …

This https://arxiv.org/abs/2212.01551 has been replaced.
link: https://scholar.google.com/scholar?q=a

Quantify the Causes of Causal Emergence: Critical Conditions of Uncertainty and Asymmetry in Causal Structure
Beneficial to advanced computing devices, models with massive parameters are increasingly employed to extract more information to enhance the precision in describing and predicting the patterns of objective systems. This phenomenon is particularly pronounced in research domains associated with deep learning. However, investigations of causal relationships based on statistical and informational theories have posed an interesting and valuable challenge to large-scale models in the recent decade. …

This https://arxiv.org/abs/2008.10796 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Variational Network Toward Blind Image Restoration
Blind image restoration (IR) is a common yet challenging problem in computer vision. Classical model-based methods and recent deep learning (DL)-based methods represent two different methodologies for this problem, each with their own merits and drawbacks. In this paper, we propose a novel blind image restoration method, aiming to integrate both the advantages of them. Specifically, we construct a general Bayesian generative model for the blind IR, which explicitly depicts the degradation proce…

This https://arxiv.org/abs/2309.02050 has been replaced.
link: https://scholar.google.com/scholar?q=a

Machine learning of network inference enhancement from noisy measurements
Inferring networks from observed time series data presents a clear glimpse into the interconnections among nodes. Network inference models, when dealing with real-world open cases, especially in the presence of observational noise, experience a sharp decline in performance, significantly undermining their practical applicability. We find that in real-world scenarios, noisy samples cause parameter updates in network inference models to deviate from the correct direction, leading to a degradation…

This https://arxiv.org/abs/2403.02131 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution
Evolutionary algorithms, such as Differential Evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts in algorithm selection or configuration. This paper aims to address the limitation by leveraging the complementary strengths of a group of algorithms and dynamically scheduling them throughout the optimization progress for specific problems. We propose a dee…

This https://arxiv.org/abs/2401.07698 has been replaced.
link: https://scholar.google.com/scholar?q=a

Online Learning of Continuous Signed Distance Fields Using Piecewise Polynomials
Reasoning about distance is indispensable for establishing or avoiding contact in manipulation tasks. To this end, we present an online approach for learning implicit representations of signed distance using piecewise polynomial basis functions. Starting from an arbitrary prior shape, our method incrementally constructs a continuous and smooth distance representation from incoming surface points, with analytical access to gradient information. The underlying model does not store training data f…

This https://arxiv.org/abs/2309.13734 has been replaced.
link: https://scholar.google.com/scholar?q=a

Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classification
Stance classification, the task of predicting the viewpoint of an author on a subject of interest, has long been a focal point of research in domains ranging from social science to machine learning. Current stance detection methods rely predominantly on manual annotation of sentences, followed by training a supervised machine learning model. However, this manual annotation process requires laborious annotation effort, and thus hampers its potential to generalize across different contexts. In th…

This https://arxiv.org/abs/2211.03102 has been replaced.
link: https://scholar.google.com/scholar?q=a

Collaborative Video Analytics on Distributed Edges with Multiagent Deep Reinforcement Learning
Deep Neural Network (DNN) based video analytics empowers many computer vision-based applications to achieve high recognition accuracy. To reduce inference delay and bandwidth cost for video analytics, the DNN models can be deployed on the edge nodes, which are proximal to end users. However, the processing capacity of an edge node is limited, potentially incurring substantial delay if the inference requests on an edge node is overloaded. While efforts have been made to enhance video analytics b…

Regularized Q-learning through Robust Averaging
Peter Schmitt-F\"orster, Tobias Sutter
https://arxiv.org/abs/2405.02201 https://…

Regularized Q-learning through Robust Averaging
We propose a new Q-learning variant, called 2RA Q-learning, that addresses some weaknesses of existing Q-learning methods in a principled manner. One such weakness is an underlying estimation bias which cannot be controlled and often results in poor performance. We propose a distributionally robust estimator for the maximum expected value term, which allows us to precisely control the level of estimation bias introduced. The distributionally robust estimator admits a closed-form solution such t…

This https://arxiv.org/abs/2205.07739 has been replaced.
link: https://scholar.google.com/scholar?q=a

The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data
Self-training (ST) is a simple yet effective semi-supervised learning method. However, why and how ST improves generalization performance by using potentially erroneous pseudo-labels is still not well understood. To deepen the understanding of ST, we derive and analyze a sharp characterization of the behavior of iterative ST when training a linear classifier by minimizing the ridge-regularized convex loss on binary Gaussian mixtures, in the asymptotic limit where input dimension and data size d…

This https://arxiv.org/abs/2207.09098 has been replaced.
link: https://scholar.google.com/scholar?q=a

ReBoot: Distributed statistical learning via refitting bootstrap samples
In this paper, we propose a one-shot distributed learning algorithm via refitting bootstrap samples, which we refer to as ReBoot. ReBoot refits a new model to mini-batches of bootstrap samples that are continuously drawn from each of the locally fitted models. It requires only one round of communication of model parameters without much memory. Theoretically, we analyze the statistical error rate of ReBoot for generalized linear models (GLM) and noisy phase retrieval, which represent convex and …

This https://arxiv.org/abs/2210.01988 has been replaced.
link: https://scholar.google.com/scholar?q=a

Bicoptor: Two-round Secure Three-party Non-linear Computation without Preprocessing for Privacy-preserving Machine Learning
The overhead of non-linear functions dominates the performance of the secure multiparty computation (MPC) based privacy-preserving machine learning (PPML). This work introduces a family of novel secure three-party computation (3PC) protocols, Bicoptor, which improve the efficiency of evaluating non-linear functions. The basis of Bicoptor is a new sign determination protocol, which relies on a clever use of the truncation protocol proposed in SecureML (S\&P 2017). Our 3PC sign determination prot…

This https://arxiv.org/abs/2402.04154 has been replaced.
link: https://scholar.google.com/scholar?q=a

Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction
Developing a generalist agent is a longstanding objective in artificial intelligence. Previous efforts utilizing extensive offline datasets from various tasks demonstrate remarkable performance in multitasking scenarios within Reinforcement Learning. However, these works encounter challenges in extending their capabilities to new tasks. Recent approaches integrate textual guidance or visual trajectory into decision networks to provide task-specific contextual cues, representing a promising dire…

This https://arxiv.org/abs/2310.05865 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Learning-Based Framework for Safe Human-Robot Collaboration with Multiple Backup Control Barrier Functions
Ensuring robot safety in complex environments is a difficult task due to actuation limits, such as torque bounds. This paper presents a safety-critical control framework that leverages learning-based switching between multiple backup controllers to formally guarantee safety under bounded control inputs while satisfying driver intention. By leveraging backup controllers designed to uphold safety and input constraints, backup control barrier functions (BCBFs) construct implicitly defined control …

This https://arxiv.org/abs/2208.05716 has been replaced.
link: https://scholar.google.com/scholar?q=a

Task Aligned Meta-learning based Augmented Graph for Cold-Start Recommendation
The cold-start problem is a long-standing challenge in recommender systems due to the lack of user-item interactions, which significantly hurts the recommendation effect over new users and items. Recently, meta-learning based methods attempt to learn globally shared prior knowledge across all users, which can be rapidly adapted to new users and items with very few interactions. Though with significant performance improvement, the globally shared parameter may lead to local optimum. Besides, the…

This https://arxiv.org/abs/2111.05778 has been replaced.
link: https://scholar.google.com/scholar?q=a

Theoretical and Empirical Analysis of a Fast Algorithm for Extracting Polygons from Signed Distance Bounds
Recently there has been renewed interest in signed distance bound representations due to their unique properties for 3D shape modelling. This is especially the case for deep learning-based bounds. However, it is beneficial to work with polygons in most computer-graphics applications. Thus, in this paper we introduce and investigate an asymptotically fast method for transforming signed distance bounds into polygon meshes. This is achieved by combining the principles of sphere tracing (or ray mar…

This https://arxiv.org/abs/2404.01205 has been replaced.
link: https://scholar.google.com/scholar?q=a

Foundations of Cyber Resilience: The Confluence of Game, Control, and Learning Theories
Cyber resilience is a complementary concept to cybersecurity, focusing on the preparation, response, and recovery from cyber threats that are challenging to prevent. Organizations increasingly face such threats in an evolving cyber threat landscape. Understanding and establishing foundations for cyber resilience provide a quantitative and systematic approach to cyber risk assessment, mitigation policy evaluation, and risk-informed defense design. A systems-scientific view toward cyber risks pro…

This https://arxiv.org/abs/2404.00228 has been replaced.
link: https://scholar.google.com/scholar?q=a

InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning
Continual learning requires the model to learn multiple tasks sequentially. In continual learning, the model should possess the ability to maintain its performance on old tasks (stability) and the ability to adapt to new tasks continuously (plasticity). Recently, parameter-efficient fine-tuning (PEFT), which involves freezing a pre-trained model and injecting a small number of learnable parameters to adapt to downstream tasks, has gained increasing popularity in continual learning. Although exi…

This https://arxiv.org/abs/2207.10223 has been replaced.
link: https://scholar.google.com/scholar?q=a

Fairness Testing: A Comprehensive Survey and Analysis of Trends
Unfair behaviors of Machine Learning (ML) software have garnered increasing attention and concern among software engineers. To tackle this issue, extensive research has been dedicated to conducting fairness testing of ML software, and this paper offers a comprehensive survey of existing studies in this field. We collect 100 papers and organize them based on the testing workflow (i.e., how to test) and testing components (i.e., what to test). Furthermore, we analyze the research focus, trends, a…

This https://arxiv.org/abs/2211.03102 has been replaced.
link: https://scholar.google.com/scholar?q=a

Collaborative Video Analytics on Distributed Edges with Multiagent Deep Reinforcement Learning
Deep Neural Network (DNN) based video analytics empowers many computer vision-based applications to achieve high recognition accuracy. To reduce inference delay and bandwidth cost for video analytics, the DNN models can be deployed on the edge nodes, which are proximal to end users. However, the processing capacity of an edge node is limited, potentially incurring substantial delay if the inference requests on an edge node is overloaded. While efforts have been made to enhance video analytics b…

This https://arxiv.org/abs/2310.05865 has been replaced.
link: https://scholar.google.com/scholar?q=a

A Learning-Based Framework for Safe Human-Robot Collaboration with Multiple Backup Control Barrier Functions
Ensuring robot safety in complex environments is a difficult task due to actuation limits, such as torque bounds. This paper presents a safety-critical control framework that leverages learning-based switching between multiple backup controllers to formally guarantee safety under bounded control inputs while satisfying driver intention. By leveraging backup controllers designed to uphold safety and input constraints, backup control barrier functions (BCBFs) construct implicitly defined control …

This https://arxiv.org/abs/2402.03077 has been replaced.
link: https://scholar.google.com/scholar?q=a

Markov Persuasion Processes: Learning to Persuade from Scratch
In Bayesian persuasion, an informed sender strategically discloses information to a receiver so as to persuade them to undertake desirable actions. Recently, a growing attention has been devoted to settings in which sender and receivers interact sequentially. Recently, Markov persuasion processes (MPPs) have been introduced to capture sequential scenarios where a sender faces a stream of myopic receivers in a Markovian environment. The MPPs studied so far in the literature suffer from issues th…

This https://arxiv.org/abs/2311.14213 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning to Solve Inverse Problems for Perceptual Sound Matching
Perceptual sound matching (PSM) aims to find the input parameters to a synthesizer so as to best imitate an audio target. Deep learning for PSM optimizes a neural network to analyze and reconstruct prerecorded samples. In this context, our article addresses the problem of designing a suitable loss function when the training set is generated by a differentiable synthesizer. Our main contribution is perceptual-neural-physical loss (PNP), which aims at addressing a tradeoff between perceptual rele…

This https://arxiv.org/abs/2309.01243 has been replaced.
link: https://scholar.google.com/scholar?q=a

The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning
To achieve differential privacy (DP) one typically randomizes the output of the underlying query. In big data analytics, one often uses randomized sketching/aggregation algorithms to make processing high-dimensional data tractable. Intuitively, such machine learning (ML) algorithms should provide some inherent privacy, yet most if not all existing DP mechanisms do not leverage this inherent randomness, resulting in potentially redundant noising. The motivating question of our work is: (How)…

This https://arxiv.org/abs/2206.13090 has been replaced.
link: https://scholar.google.com/scholar?q=a

Variance Reduced Random Relaxed Projection Method for Constrained Finite-sum Minimization Problems
For many applications in signal processing and machine learning, we are tasked with minimizing a large sum of convex functions subject to a large number of convex constraints. In this paper, we devise a new random projection method (RPM) to efficiently solve this problem. Compared with existing RPMs, our proposed algorithm features two useful algorithmic ideas. First, at each iteration, instead of projecting onto the subset defined by one of the constraints, our algorithm only requires projecti…

This https://arxiv.org/abs/2404.15888 has been replaced.
link: https://scholar.google.com/scholar?q=a

Near-Optimal Wafer-Scale Reduce
Efficient Reduce and AllReduce communication collectives are a critical cornerstone of high-performance computing (HPC) applications. We present the first systematic investigation of Reduce and AllReduce on the Cerebras Wafer-Scale Engine (WSE). This architecture has been shown to achieve unprecedented performance both for machine learning workloads and other computational problems like FFT. We introduce a performance model to estimate the execution time of algorithms on the WSE and validate ou…

This https://arxiv.org/abs/2402.01059 has been replaced.
link: https://scholar.google.com/scholar?q=a

Eco-driving under localization uncertainty for connected vehicles on Urban roads: Data-driven approach and Experiment verification
This paper addresses the eco-driving problem for connected vehicles on urban roads, considering localization uncertainty. Eco-driving is defined as longitudinal speed planning and control on roads with the presence of a sequence of traffic lights. We solve the problem by using a data-driven model predictive control (MPC) strategy. This approach involves learning a cost-to-go function and constraints from state-input data. The cost-to-go function represents the remaining energy-to-spend from the…

Q-learning-based Opportunistic Communication for Real-time Mobile Air Quality Monitoring Systems
Trung Thanh Nguyen, Truong Thao Nguyen, Dinh Tuan Anh Nguyen, Thanh Hung Nguyen, Phi Le Nguyen
https://arxiv.org/abs/2405.01609

Q-learning-based Opportunistic Communication for Real-time Mobile Air Quality Monitoring Systems
We focus on real-time air quality monitoring systems that rely on devices installed on automobiles in this research. We investigate an opportunistic communication model in which devices can send the measured data directly to the air quality server through a 4G communication channel or via Wi-Fi to adjacent devices or the so-called Road Side Units deployed along the road. We aim to reduce 4G costs while assuring data latency, where the data latency is defined as the amount of time it takes for d…

This https://arxiv.org/abs/2403.01636 has been replaced.
link: https://scholar.google.com/scholar?q=a

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Multitask Reinforcement Learning (MTRL) approaches have gained increasing attention for its wide applications in many important Reinforcement Learning (RL) tasks. However, while recent advancements in MTRL theory have focused on the improved statistical efficiency by assuming a shared structure across tasks, exploration--a crucial aspect of RL--has been largely overlooked. This paper addresses this gap by showing that when an agent is trained on a sufficiently diverse set of tasks, a generic po…

This https://arxiv.org/abs/2404.15523 has been replaced.
link: https://scholar.google.com/scholar?q=a

Understanding Hyperbolic Metric Learning through Hard Negative Sampling
In recent years, there has been a growing trend of incorporating hyperbolic geometry methods into computer vision. While these methods have achieved state-of-the-art performance on various metric learning tasks using hyperbolic distance measurements, the underlying theoretical analysis supporting this superior performance remains under-exploited. In this study, we investigate the effects of integrating hyperbolic space into metric learning, particularly when training with contrastive loss. We i…

Superior Genetic Algorithms for the Target Set Selection Problem Based on Power-Law Parameter Choices and Simple Greedy Heuristics
Benjamin Doerr, Martin S. Krejca, Nguyen Vu
https://arxiv.org/abs/2404.04018

Superior Genetic Algorithms for the Target Set Selection Problem Based on Power-Law Parameter Choices and Simple Greedy Heuristics
The target set selection problem (TSS) asks for a set of vertices such that an influence spreading process started in these vertices reaches the whole graph. The current state of the art for this NP-hard problem are three recently proposed randomized search heuristics, namely a biased random-key genetic algorithm (BRKGA) obtained from extensive parameter tuning, a max-min ant system (MMAS), and a MMAS using Q-learning with a graph convolutional network. We show that the BRKGA with two simple …

This https://arxiv.org/abs/2201.12900 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Optimal Topology for Ad-hoc Robot Networks
In this paper, we synthesize a data-driven method to predict the optimal topology of an ad-hoc robot network. This problem is technically a multi-task classification problem. However, we divide it into a class of multi-class classification problems that can be more efficiently solved. For this purpose, we first compose an algorithm to create ground-truth optimal topologies associated with various configurations of a robot network. This algorithm incorporates a complex collection of optimality c…

This https://arxiv.org/abs/2011.10814 has been replaced.
link: https://scholar.google.com/scholar?q=a

Minimax Adaptive Control for a Finite Set of Linear Systems
An adaptive controller with bounded l2-gain from disturbances to errors is derived for linear time-invariant systems with uncertain parameters restricted to a finite set. The gain bound refers to the closed loop system, including the non-linear learning procedure. As a result, robustness to unmodelled dynamics (possibly nonlinear and infinite-dimensional) follows from the small gain theorem. The approach is based on a new zero-sum dynamic game formulation, which optimizes the trade-off between …

This https://arxiv.org/abs/2402.03077 has been replaced.
link: https://scholar.google.com/scholar?q=a

Markov Persuasion Processes: Learning to Persuade from Scratch
In Bayesian persuasion, an informed sender strategically discloses information to a receiver so as to persuade them to undertake desirable actions. Recently, a growing attention has been devoted to settings in which sender and receivers interact sequentially. Recently, Markov persuasion processes (MPPs) have been introduced to capture sequential scenarios where a sender faces a stream of myopic receivers in a Markovian environment. The MPPs studied so far in the literature suffer from issues th…

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 paper, 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 concurrently…

This https://arxiv.org/abs/2403.01636 has been replaced.
link: https://scholar.google.com/scholar?q=a

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
Multitask Reinforcement Learning (MTRL) approaches have gained increasing attention for its wide applications in many important Reinforcement Learning (RL) tasks. However, while recent advancements in MTRL theory have focused on the improved statistical efficiency by assuming a shared structure across tasks, exploration--a crucial aspect of RL--has been largely overlooked. This paper addresses this gap by showing that when an agent is trained on a sufficiently diverse set of tasks, a generic po…

This https://arxiv.org/abs/2404.10073 has been replaced.
link: https://scholar.google.com/scholar?q=a

Explainable Light-Weight Deep Learning Pipeline for Improved Drought Stress Identification
Early identification of drought stress in crops is vital for implementing effective mitigation measures and reducing yield loss. Non-invasive imaging techniques hold immense potential by capturing subtle physiological changes in plants under water deficit. Sensor based imaging data serves as a rich source of information for machine learning and deep learning algorithms, facilitating further analysis aimed at identifying drought stress. While these approaches yield favorable results, real-time f…

This https://arxiv.org/abs/2201.12900 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Optimal Topology for Ad-hoc Robot Networks
In this paper, we synthesize a data-driven method to predict the optimal topology of an ad-hoc robot network. This problem is technically a multi-task classification problem. However, we divide it into a class of multi-class classification problems that can be more efficiently solved. For this purpose, we first compose an algorithm to create ground-truth optimal topologies associated with various configurations of a robot network. This algorithm incorporates a complex collection of optimality c…

This https://arxiv.org/abs/2404.00450 has been replaced.
link: https://scholar.google.com/scholar?q=a

Planning and Editing What You Retrieve for Enhanced Tool Learning
Recent advancements in integrating external tools with Large Language Models (LLMs) have opened new frontiers, with applications in mathematical reasoning, code generators, and smart assistants. However, existing methods, relying on simple one-time retrieval strategies, fall short on effectively and accurately shortlisting relevant tools. This paper introduces a novel PLUTO (Planning, Learning, and Understanding for TOols) approach, encompassing `Plan-and-Retrieve (P&R)` and `Edit-and-Ground (E…

Superior Genetic Algorithms for the Target Set Selection Problem Based on Power-Law Parameter Choices and Simple Greedy Heuristics
Benjamin Doerr, Martin S. Krejca, Nguyen Vu
https://arxiv.org/abs/2404.04018

Superior Genetic Algorithms for the Target Set Selection Problem Based on Power-Law Parameter Choices and Simple Greedy Heuristics
The target set selection problem (TSS) asks for a set of vertices such that an influence spreading process started in these vertices reaches the whole graph. The current state of the art for this NP-hard problem are three recently proposed randomized search heuristics, namely a biased random-key genetic algorithm (BRKGA) obtained from extensive parameter tuning, a max-min ant system (MMAS), and a MMAS using Q-learning with a graph convolutional network. We show that the BRKGA with two simple …

This https://arxiv.org/abs/2209.01710 has been replaced.
link: https://scholar.google.com/scholar?q=a

Perception Simplex: Verifiable Collision Avoidance in Autonomous Vehicles Amidst Obstacle Detection Faults
Advances in deep learning have revolutionized cyber-physical applications, including the development of Autonomous Vehicles. However, real-world collisions involving autonomous control of vehicles have raised significant safety concerns regarding the use of Deep Neural Networks (DNN) in safety-critical tasks, particularly Perception. The inherent unverifiability of DNNs poses a key challenge in ensuring their safe and reliable operation. In this work, we propose Perception Simplex (PS), a fau…

This https://arxiv.org/abs/2109.11762 has been replaced.
link: https://scholar.google.com/scholar?q=a

LIBRA: Enabling Workload-aware Multi-dimensional Network Topology Optimization for Distributed Training of Large AI Models
As model sizes in machine learning continue to scale, distributed training is necessary to accommodate model weights within each device and to reduce training time. However, this comes with the expense of increased communication overhead due to the exchange of gradients and activations, which become the critical bottleneck of the end-to-end training process. In this work, we motivate the design of multi-dimensional networks within machine learning systems as a cost-efficient mechanism to enhanc…

This https://arxiv.org/abs/2209.01710 has been replaced.
link: https://scholar.google.com/scholar?q=a

Perception Simplex: Verifiable Collision Avoidance in Autonomous Vehicles Amidst Obstacle Detection Faults
Advances in deep learning have revolutionized cyber-physical applications, including the development of Autonomous Vehicles. However, real-world collisions involving autonomous control of vehicles have raised significant safety concerns regarding the use of Deep Neural Networks (DNN) in safety-critical tasks, particularly Perception. The inherent unverifiability of DNNs poses a key challenge in ensuring their safe and reliable operation. In this work, we propose Perception Simplex (PS), a fau…

This https://arxiv.org/abs/2312.01183 has been replaced.
link: https://scholar.google.com/scholar?q=a

Comprehensive Robotic Cholecystectomy Dataset (CRCD): Integrating Kinematics, Pedal Signals, and Endoscopic Videos
In recent years, the potential applications of machine learning to Minimally Invasive Surgery (MIS) have spurred interest in data sets that can be used to develop data-driven tools. This paper introduces a novel dataset recorded during ex vivo pseudo-cholecystectomy procedures on pig livers, utilizing the da Vinci Research Kit (dVRK). Unlike current datasets, ours bridges a critical gap by offering not only full kinematic data but also capturing all pedal inputs used during the procedure and pr…

This https://arxiv.org/abs/2403.01528 has been replaced.
link: https://scholar.google.com/scholar?q=a

Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey
The integration of biomolecular modeling with natural language (BL) has emerged as a promising interdisciplinary area at the intersection of artificial intelligence, chemistry and biology. This approach leverages the rich, multifaceted descriptions of biomolecules contained within textual data sources to enhance our fundamental understanding and enable downstream computational tasks such as biomolecule property prediction. The fusion of the nuanced narratives expressed through natural language …

This https://arxiv.org/abs/2401.03629 has been replaced.
link: https://scholar.google.com/scholar?q=a

DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety Enhancement
Decision-making stands as a pivotal component in the realm of autonomous vehicles (AVs), playing a crucial role in navigating the intricacies of autonomous driving. Amidst the evolving landscape of data-driven methodologies, enhancing decision-making performance in complex scenarios has emerged as a prominent research focus. Despite considerable advancements, current learning-based decision-making approaches exhibit potential for refinement, particularly in aspects of policy articulation and sa…

This https://arxiv.org/abs/2403.02131 has been replaced.
link: https://scholar.google.com/scholar?q=a

Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution
Evolutionary algorithms, such as Differential Evolution, excel in solving real-parameter optimization challenges. However, the effectiveness of a single algorithm varies across different problem instances, necessitating considerable efforts in algorithm selection or configuration. This paper aims to address the limitation by leveraging the complementary strengths of a group of algorithms and dynamically scheduling them throughout the optimization progress for specific problems. We propose a dee…

This https://arxiv.org/abs/2401.03629 has been replaced.
link: https://scholar.google.com/scholar?q=a

DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety Enhancement
Decision-making stands as a pivotal component in the realm of autonomous vehicles (AVs), playing a crucial role in navigating the intricacies of autonomous driving. Amidst the evolving landscape of data-driven methodologies, enhancing decision-making performance in complex scenarios has emerged as a prominent research focus. Despite considerable advancements, current learning-based decision-making approaches exhibit potential for refinement, particularly in aspects of policy articulation and sa…

This https://arxiv.org/abs/2203.07831 has been replaced.
link: https://scholar.google.com/scholar?q=a

Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model
Graph Neural Networks (GNNs), particularly Graph Convolutional Neural Networks (GCNNs), have emerged as pivotal instruments in machine learning and signal processing for processing graph-structured data. This paper proposes an analysis framework to investigate the sensitivity of GCNNs to probabilistic graph perturbations, directly impacting the graph shift operator (GSO). Our study establishes tight expected GSO error bounds, which are explicitly linked to the error model parameters, and reveal…

This https://arxiv.org/abs/2105.13857 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Approximate and Exact Numeral Systems via Reinforcement Learning
Recent work (Xu et al., 2020) has suggested that numeral systems in different languages are shaped by a functional need for efficient communication in an information-theoretic sense. Here we take a learning-theoretic approach and show how efficient communication emerges via reinforcement learning. In our framework, two artificial agents play a Lewis signaling game where the goal is to convey a numeral concept. The agents gradually learn to communicate using reinforcement learning and the result…

This https://arxiv.org/abs/2201.06317 has been replaced.
link: https://scholar.google.com/scholar?q=a

Language Model-Based Paired Variational Autoencoders for Robotic Language Learning
Human infants learn language while interacting with their environment in which their caregivers may describe the objects and actions they perform. Similar to human infants, artificial agents can learn language while interacting with their environment. In this work, first, we present a neural model that bidirectionally binds robot actions and their language descriptions in a simple object manipulation scenario. Building on our previous Paired Variational Autoencoders (PVAE) model, we demonstrate…

This https://arxiv.org/abs/2403.01766 has been replaced.
link: https://scholar.google.com/scholar?q=a

Improving Visual Perception of a Social Robot for Controlled and In-the-wild Human-robot Interaction
Social robots often rely on visual perception to understand their users and the environment. Recent advancements in data-driven approaches for computer vision have demonstrated great potentials for applying deep-learning models to enhance a social robot's visual perception. However, the high computational demands of deep-learning methods, as opposed to the more resource-efficient shallow-learning models, bring up important questions regarding their effects on real-world interaction and user exp…

This https://arxiv.org/abs/2209.08349 has been replaced.
link: https://scholar.google.com/scholar?q=a

Unguided Self-exploration in Narrow Spaces with Safety Region Enhanced Reinforcement Learning for Ackermann-steering Robots
In narrow spaces, motion planning based on the traditional hierarchical autonomous system could cause collisions due to mapping, localization, and control noises, especially for car-like Ackermann-steering robots which suffer from non-convex and non-holonomic kinematics. To tackle these problems, we leverage deep reinforcement learning which is verified to be effective in self-decision-making, to self-explore in narrow spaces without a given map and destination while avoiding collisions. Specif…

This https://arxiv.org/abs/2402.16796 has been replaced.
link: https://scholar.google.com/scholar?q=a

Expressive Whole-Body Control for Humanoid Robots
Can we enable humanoid robots to generate rich, diverse, and expressive motions in the real world? We propose to learn a whole-body control policy on a human-sized robot to mimic human motions as realistic as possible. To train such a policy, we leverage the large-scale human motion capture data from the graphics community in a Reinforcement Learning framework. However, directly performing imitation learning with the motion capture dataset would not work on the real humanoid robot, given the la…

This https://arxiv.org/abs/2309.14246 has been replaced.
link: https://scholar.google.com/scholar?q=a

Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning
Deployment in hazardous environments requires robots to understand the risks associated with their actions and movements to prevent accidents. Despite its importance, these risks are not explicitly modeled by currently deployed locomotion controllers for legged robots. In this work, we propose a risk sensitive locomotion training method employing distributional reinforcement learning to consider safety explicitly. Instead of relying on a value expectation, we estimate the complete value distrib…

This https://arxiv.org/abs/2309.14225 has been replaced.
link: https://scholar.google.com/scholar?q=a

HumanMimic: Learning Natural Locomotion and Transitions for Humanoid Robot via Wasserstein Adversarial Imitation
Transferring human motion skills to humanoid robots remains a significant challenge. In this study, we introduce a Wasserstein adversarial imitation learning system, allowing humanoid robots to replicate natural whole-body locomotion patterns and execute seamless transitions by mimicking human motions. First, we present a unified primitive-skeleton motion retargeting to mitigate morphological differences between arbitrary human demonstrators and humanoid robots. An adversarial critic component …