English
Related papers

Related papers: Reinforcement Learning with Wasserstein Distance R…

200 papers

Policy gradients methods often achieve better performance when the change in policy is limited to a small Kullback-Leibler divergence. We derive policy gradients where the change in policy is limited to a small Wasserstein distance (or…

Machine Learning · Computer Science 2017-12-21 Pierre H. Richemond , Brendan Maginnis

We develop a projected Wasserstein distance for the two-sample test, a fundamental problem in statistics and machine learning: given two sets of samples, to determine whether they are from the same distribution. In particular, we aim to…

Machine Learning · Statistics 2024-04-01 Jie Wang , Rui Gao , Yao Xie

We present a geometric framework for Reinforcement Learning (RL) that views policies as maps into the Wasserstein space of action probabilities. First, we define a Riemannian structure induced by stationary distributions, proving its…

Machine Learning · Computer Science 2026-04-17 Mathias Dus

Motivated by the statistical and computational challenges of computing Wasserstein distances in high-dimensional contexts, machine learning researchers have defined modified Wasserstein distances based on computing distances between…

Probability · Mathematics 2022-06-02 Jiaqi Xi , Jonathan Niles-Weed

Noisy labels often occur in vision datasets, especially when they are obtained from crowdsourcing or Web scraping. We propose a new regularization method, which enables learning robust classifiers in presence of noisy data. To achieve this…

Machine Learning · Computer Science 2021-06-30 Kilian Fatras , Bharath Bhushan Damodaran , Sylvain Lobry , Rémi Flamary , Devis Tuia , Nicolas Courty

The Wasserstein distance has emerged as a key metric to quantify distances between probability distributions, with applications in various fields, including machine learning, control theory, decision theory, and biological systems.…

Machine Learning · Computer Science 2026-02-10 Eduardo Figueiredo , Steven Adams , Luca Laurenti

One approach to matching texts from asymmetrical domains is projecting the input sequences into a common semantic space as feature vectors upon which the matching function can be readily defined and learned. In real-world matching…

Computation and Language · Computer Science 2020-10-20 Weijie Yu , Chen Xu , Jun Xu , Liang Pang , Xiaopeng Gao , Xiaozhao Wang , Ji-Rong Wen

We consider machine learning, particularly regression, using locally-differentially private datasets. The Wasserstein distance is used to define an ambiguity set centered at the empirical distribution of the dataset corrupted by local…

Machine Learning · Computer Science 2020-06-25 Farhad Farokhi

Large language models (LLMs) are commonly aligned with human preferences using reinforcement learning from human feedback (RLHF). In this method, LLM policies are generally optimized through reward maximization with Kullback-Leibler (KL)…

Machine Learning · Computer Science 2026-02-03 Byeonghu Na , Hyungho Na , Yeongmin Kim , Suhyeon Jo , HeeSun Bae , Mina Kang , Il-Chul Moon

The empirical success of distributional reinforcement learning (RL) highly relies on the choice of distribution divergence equipped with an appropriate distribution representation. In this paper, we propose \textit{Sinkhorn distributional…

Machine Learning · Computer Science 2024-10-16 Ke Sun , Yingnan Zhao , Wulong Liu , Bei Jiang , Linglong Kong

We study policy gradient methods for continuous-action, entropy-regularized reinforcement learning through the lens of Wasserstein geometry. Starting from a Wasserstein proximal update, we derive Wasserstein Proximal Policy Gradient (WPPG)…

Machine Learning · Computer Science 2026-03-04 Zhaoyu Zhu , Shuhan Zhang , Rui Gao , Shuang Li

The Wasserstein metric is an important measure of distance between probability distributions, with applications in machine learning, statistics, probability theory, and data analysis. This paper provides upper and lower bounds on…

Statistics Theory · Mathematics 2019-11-11 Shashank Singh , Barnabás Póczos

A novel optimization approach is proposed for application to policy gradient methods and evolution strategies for reinforcement learning (RL). The procedure uses a computationally efficient Wasserstein natural gradient (WNG) descent that…

Machine Learning · Computer Science 2021-03-19 Ted Moskovitz , Michael Arbel , Ferenc Huszar , Arthur Gretton

We define a modified Wasserstein distance for distribution clustering which inherits many of the properties of the Wasserstein distance but which can be estimated easily and computed quickly. The modified distance is the sum of two terms.…

Methodology · Statistics 2018-12-31 Isabella Verdinelli , Larry Wasserman

Issued from Optimal Transport, the Wasserstein distance has gained importance in Machine Learning due to its appealing geometrical properties and the increasing availability of efficient approximations. In this work, we consider the problem…

Machine Learning · Statistics 2022-02-21 Guillaume Staerman , Pierre Laforgue , Pavlo Mozharovskyi , Florence d'Alché-Buc

Unsupervised reinforcement learning aims to train agents to learn a handful of policies or skills in environments without external reward. These pre-trained policies can accelerate learning when endowed with external reward, and can also be…

Machine Learning · Computer Science 2021-10-18 Shuncheng He , Yuhang Jiang , Hongchang Zhang , Jianzhun Shao , Xiangyang Ji

Personalized recommender systems are playing an increasingly important role as more content and services become available and users struggle to identify what might interest them. Although matrix factorization and deep learning based methods…

Information Retrieval · Computer Science 2021-01-14 Chen Ma , Liheng Ma , Yingxue Zhang , Ruiming Tang , Xue Liu , Mark Coates

Optimal Transport (OT) metrics allow for defining discrepancies between two probability measures. Wasserstein distance is for longer the celebrated OT-distance frequently-used in the literature, which seeks probability distributions to be…

Machine Learning · Computer Science 2021-10-14 Mokhtar Z. Alaya , Gilles Gasso , Maxime Berar , Alain Rakotomamonjy

We propose to align distributional data from the perspective of Wasserstein means. We raise the problem of regularizing Wasserstein means and propose several terms tailored to tackle different problems. Our formulation is based on the…

Machine Learning · Computer Science 2020-02-24 Liang Mi , Wen Zhang , Yalin Wang

Wasserstein distributionally robust optimization (DRO) has recently achieved empirical success for various applications in operations research and machine learning, owing partly to its regularization effect. Although connection between…

Machine Learning · Computer Science 2020-11-02 Rui Gao , Xi Chen , Anton J. Kleywegt