English
Related papers

Related papers: Stabilizing Q Learning Via Soft Mellowmax Operator

200 papers

Evaluating the log-sum-exp function or the softmax function is a key step in many modern data science algorithms, notably in inference and classification. Because of the exponentials that these functions contain, the evaluation is prone to…

Numerical Analysis · Mathematics 2019-09-10 Pierre Blanchard , Desmond J. Higham , Nicholas J. Higham

Multi-agent systems of large language models (LLMs) show promise for complex reasoning, but their effectiveness is often limited by fixed collaboration protocols. These frameworks typically focus on macro-level orchestration while…

Artificial Intelligence · Computer Science 2025-12-10 Wei Yang , Jesse Thomason

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal…

Machine Learning · Computer Science 2026-03-17 Ming Wen , Kun Yang , Xin Chen , Jingyu Zhang , Dingding Han , Shiwen Cui , Yuedong Xu

Smoothed analysis is a framework for analyzing the complexity of an algorithm, acting as a bridge between average and worst-case behaviour. For example, Quicksort and the Simplex algorithm are widely used in practical applications, despite…

Machine Learning · Computer Science 2015-03-29 Bichen Shi , Michel Schellekens , Georgiana Ifrim

Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure. Such instance-specific behavior is not captured by existing global minimax…

Machine Learning · Statistics 2021-06-29 Koulik Khamaru , Eric Xia , Martin J. Wainwright , Michael I. Jordan

Scaling up the model size and computation has brought consistent performance improvements in supervised learning. However, this lesson often fails to apply to reinforcement learning (RL) because training the model on non-stationary data…

Machine Learning · Computer Science 2025-05-30 Hojoon Lee , Youngdo Lee , Takuma Seno , Donghu Kim , Peter Stone , Jaegul Choo

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on…

The analysis in Part I revealed interesting properties for subgradient learning algorithms in the context of stochastic optimization when gradient noise is present. These algorithms are used when the risk functions are non-smooth and…

Optimization and Control · Mathematics 2017-04-21 Bicheng Ying , Ali H. Sayed

In federated learning (FL), a cluster of local clients are chaired under the coordination of the global server and cooperatively train one model with privacy protection. Due to the multiple local updates and the isolated non-iid dataset,…

Machine Learning · Computer Science 2024-04-02 Yan Sun , Li Shen , Shixiang Chen , Liang Ding , Dacheng Tao

In this paper, we introduce some adaptive methods for solving variational inequalities with relatively strongly monotone operators. Firstly, we focus on the modification of the recently proposed, in smooth case [1], adaptive numerical…

Optimization and Control · Mathematics 2022-11-01 A. A. Titov , S. S. Ablaev , M. S. Alkousa , F. S. Stonyakin , A. V. Gasnikov

A learning-to-defer (L2D) system decides, for each input, whether to predict on its own or to hand it to one of several available experts. The very well established recipe trains classifier and router jointly by treating the $K$ classes and…

Machine Learning · Statistics 2026-05-29 Yannis Montreuil , Axel Carlier , Lai Xing Ng , Wei Tsang Ooi

Modern neural networks are often augmented with an attention mechanism, which tells the network where to focus within the input. We propose in this paper a new framework for sparse and structured attention, building upon a smoothed max…

Machine Learning · Statistics 2019-02-26 Vlad Niculae , Mathieu Blondel

This paper addresses the distributed stochastic minimax optimization problem subject to stochastic constraints. We propose a novel first-order Softmax-Weighted Switching Gradient method tailored for federated learning. Under full client…

Machine Learning · Computer Science 2026-03-09 Zhankun Luo , Antesh Upadhyay , Sang Bin Moon , Abolfazl Hashemi

Covariate shift occurs when the distribution of input features differs between the training and testing phases. In covariate shift, estimating an unknown function's moment is a classical problem that remains under-explored, despite its…

Machine Learning · Statistics 2025-07-01 Zhen Zhang , Xin Liu , Shaoli Wang , Jiaye Teng

Soft dynamic time warping (SDTW) is a differentiable loss function that allows for training neural networks from weakly aligned data. Typically, SDTW is used to iteratively compute and refine soft alignments that compensate for temporal…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-11 Johannes Zeitler , Simon Deniffel , Michael Krause , Meinard Müller

We study the problem of solving fixed-point equations for seminorm-contractive operators and establish foundational results on the non-asymptotic behavior of iterative algorithms in both deterministic and stochastic settings. Specifically,…

Machine Learning · Computer Science 2025-02-21 Zaiwei Chen , Sheng Zhang , Zhe Zhang , Shaan Ul Haque , Siva Theja Maguluri

We introduce a new paradigm for solving regularized variational problems. These are typically formulated to address ill-posed inverse problems encountered in signal and image processing. The objective function is traditionally defined by…

Optimization and Control · Mathematics 2021-04-22 Jean-Christophe Pesquet , Audrey Repetti , Matthieu Terris , Yves Wiaux

This paper proposes a framework to study the convergence of stochastic optimization and learning algorithms. The framework is modeled over the different challenges that these algorithms pose, such as (i) the presence of random additive…

Optimization and Control · Mathematics 2024-07-01 Nicola Bastianello , Liam Madden , Ruggero Carli , Emiliano Dall'Anese

Quantization has established itself as the primary approach for decreasing the computational and storage expenses associated with Large Language Models (LLMs) inference. The majority of current research emphasizes quantizing weights and…

Machine Learning · Computer Science 2024-10-07 Moran Shkolnik , Maxim Fishman , Brian Chmiel , Hilla Ben-Yaacov , Ron Banner , Kfir Yehuda Levy

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical.…

Machine Learning · Computer Science 2026-02-02 Lingkai Kong , Anagha Satish , Hezi Jiang , Akseli Kangaslahti , Andrew Ma , Wenbo Chen , Mingxiao Song , Lily Xu , Milind Tambe