English
Related papers

Related papers: Stabilizing Q Learning Via Soft Mellowmax Operator

200 papers

Deep reinforcement learning (RL) has achieved great empirical successes in various domains. However, the large search space of neural networks requires a large amount of data, which makes the current RL algorithms not sample efficient.…

Machine Learning · Computer Science 2020-08-18 Qianli Shen , Yan Li , Haoming Jiang , Zhaoran Wang , Tuo Zhao

Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints. Existing methods often rely on soft expected-cost objectives or iterative generative inference, which can be…

Machine Learning · Computer Science 2026-03-17 Mumuksh Tayal , Manan Tayal , Ravi Prakash

Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise tolerance in the presence of label noise, particularly…

Machine Learning · Computer Science 2025-08-05 Jialiang Wang , Xiong Zhou , Deming Zhai , Junjun Jiang , Xiangyang Ji , Xianming Liu

Policy-gradient approaches to reinforcement learning have two common and undesirable overhead procedures, namely warm-start training and sample variance reduction. In this paper, we describe a reinforcement learning method based on a…

Machine Learning · Computer Science 2017-10-17 Nan Ding , Radu Soricut

This paper considers a stochastic linear quadratic problem for discrete-time systems with multiplicative noises over an infinite horizon. To obtain the optimal solution, we propose an online iterative algorithm of reinforcement learning…

Optimization and Control · Mathematics 2023-11-22 Hongdan Li , Lucky Qiaofeng Li , Xun Li , Zhaorong Zhang

Exponential generalization bounds with near-tight rates have recently been established for uniformly stable learning algorithms. The notion of uniform stability, however, is stringent in the sense that it is invariant to the data-generating…

Machine Learning · Statistics 2022-06-09 Xiao-Tong Yuan , Ping Li

We study a Q learning algorithm for continuous time stochastic control problems. The proposed algorithm uses the sampled state process by discretizing the state and control action spaces under piece-wise constant control processes. We show…

Optimization and Control · Mathematics 2023-03-10 Erhan Bayraktar , Ali Devran Kara

The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well. This paper provides convex lower bounds and concave upper bounds on the softmax function, which are compatible…

Machine Learning · Computer Science 2023-03-06 Dennis Wei , Haoze Wu , Min Wu , Pin-Yu Chen , Clark Barrett , Eitan Farchi

Choosing an appropriate optimization algorithm is essential to achieving success in optimization challenges. Here we present a new evolutionary algorithm structure that utilizes a reinforcement learning-based agent aimed at addressing these…

Neural and Evolutionary Computing · Computer Science 2024-04-18 Farajollah Tahernezhad-Javazm , Debbie Rankin , Naomi Du Bois , Alice E. Smith , Damien Coyle

We devise a novel method for nowcasting implied volatility based on neural operators. Better known as implied volatility smoothing in the financial industry, nowcasting of implied volatility means constructing a smooth surface that is…

Computational Finance · Quantitative Finance 2025-06-17 Ruben Wiedemann , Antoine Jacquier , Lukas Gonon

Time-series reasoning remains a significant challenge in multimodal large language models (MLLMs) due to the dynamic temporal patterns, ambiguous semantics, and lack of temporal priors. In this work, we introduce TimeMaster, a reinforcement…

Machine Learning · Computer Science 2025-06-17 Junru Zhang , Lang Feng , Xu Guo , Yuhan Wu , Yabo Dong , Duanqing Xu

This work presents the first finite-time analysis for the last-iterate convergence of average-reward $Q$-learning with an asynchronous implementation. A key feature of the algorithm we study is the use of adaptive stepsizes, which serve as…

Machine Learning · Computer Science 2026-04-07 Zaiwei Chen , Phalguni Nanda

Deep Metric Learning (DML) loss functions traditionally aim to control the forces of separability and compactness within an embedding space so that the same class data points are pulled together and different class ones are pushed apart.…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Michael G. DeMoor , John J. Prevost

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values…

Machine Learning · Computer Science 2020-10-13 Huaqing Xiong , Lin Zhao , Yingbin Liang , Wei Zhang

Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can be a bottleneck of representational capacity of neural…

Machine Learning · Statistics 2018-05-29 Sekitoshi Kanai , Yasuhiro Fujiwara , Yuki Yamanaka , Shuichi Adachi

We give sublinear-time approximation algorithms for some optimization problems arising in machine learning, such as training linear classifiers and finding minimum enclosing balls. Our algorithms can be extended to some kernelized versions…

Machine Learning · Computer Science 2010-10-22 Kenneth L. Clarkson , Elad Hazan , David P. Woodruff

In this paper, we propose StableQuant, a novel adaptive post-training quantization (PTQ) algorithm for widely used speech foundation models (SFMs). While PTQ has been successfully employed for compressing large language models (LLMs) due to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-04-22 Yeona Hong , Hyewon Han , Woo-jin Chung , Hong-Goo Kang

State-action value functions (i.e., Q-values) are ubiquitous in reinforcement learning (RL), giving rise to popular algorithms such as SARSA and Q-learning. We propose a new notion of action value defined by a Gaussian smoothed version of…

Machine Learning · Computer Science 2018-07-26 Ofir Nachum , Mohammad Norouzi , George Tucker , Dale Schuurmans

We study the performance of stochastic first-order methods for finding saddle points of convex-concave functions. A notorious challenge faced by such methods is that the gradients can grow arbitrarily large during optimization, which may…

Machine Learning · Computer Science 2024-06-10 Gergely Neu , Nneka Okolo

The problem we consider is a multi-objective optimization problem, in which the goal is to find an optimal value of a vector function representing various criteria. The aim of this work is to develop an algorithm which utilizes the trust…

Optimization and Control · Mathematics 2026-05-15 Nataša Krejić , Nataša Krklec Jerinkić , Luka Rutešić