English
Related papers

Related papers: Trust Region Policy Optimization with Optimal Tran…

200 papers

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

Bayesian optimisation (BO) is a surrogate-based optimisation technique that efficiently solves expensive black-box functions with small evaluation budgets. Recent studies consider trust regions to improve the scalability of BO approaches…

Neural and Evolutionary Computing · Computer Science 2025-11-04 Kokila Kasuni Perera , Frank Neumann , Aneta Neumann

Optimal transport (OT) finds a least cost transport plan between two probability distributions using a cost matrix defined on pairs of points. Unlike standard OT, which infers unstructured pointwise mappings, low-rank optimal transport…

Machine Learning · Computer Science 2026-03-05 Henri Schmidt , Peter Halmos , Ben Raphael

In recent years, two prominent paradigms have shaped distributionally robust optimization (DRO), modeling distributional ambiguity through $\phi$-divergences and Wasserstein distances, respectively. While the former focuses on ambiguity in…

Optimization and Control · Mathematics 2025-12-22 Jose Blanchet , Daniel Kuhn , Jiajin Li , Bahar Taskesen

The Wasserstein distance, rooted in optimal transport (OT) theory, is a popular discrepancy measure between probability distributions with various applications to statistics and machine learning. Despite their rich structure and…

Machine Learning · Statistics 2023-03-02 Sloan Nietert , Rachel Cummings , Ziv Goldfeld

Distributionally robust stochastic optimization (DRSO) is an approach to optimization under uncertainty in which, instead of assuming that there is a known true underlying probability distribution, one hedges against a chosen set of…

Optimization and Control · Mathematics 2022-05-03 Rui Gao , Anton J. Kleywegt

We introduce a novel optimal transport framework for probabilistic circuits (PCs). While it has been shown recently that divergences between distributions represented as certain classes of PCs can be computed tractably, to the best of our…

Artificial Intelligence · Computer Science 2025-10-16 Adrian Ciotinga , YooJung Choi

We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update. In addition to using the proximity of one single old policy as the normal trust…

Machine Learning · Computer Science 2022-09-19 Hung Le , Thommen Karimpanal George , Majid Abdolshah , Dung Nguyen , Kien Do , Sunil Gupta , Svetha Venkatesh

Trust region methods are a popular tool in reinforcement learning as they yield robust policy updates in continuous and discrete action spaces. However, enforcing such trust regions in deep reinforcement learning is difficult. Hence, many…

Machine Learning · Computer Science 2021-03-10 Fabian Otto , Philipp Becker , Ngo Anh Vien , Hanna Carolin Ziesche , Gerhard Neumann

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement…

Machine Learning · Computer Science 2019-12-30 Devesh Jha , Arvind Raghunathan , Diego Romeres

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates…

Machine Learning · Computer Science 2025-05-26 Ben Rahman

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent real-world user…

Machine Learning · Computer Science 2026-01-16 Zaiyan Xu , Sushil Vemuri , Kishan Panaganti , Dileep Kalathil , Rahul Jain , Deepak Ramachandran

Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscriminately truncating high-return yet high-divergence updates. We demonstrate that explicitly…

Machine Learning · Computer Science 2026-05-27 Yu Luo , Shuo Han , Yihan Hu , Lei Lv , Huaping Liu , Fuchun Sun , Jianye Hao , Dong Li

Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrifice reward…

Machine Learning · Computer Science 2025-08-18 Nikola Milosevic , Johannes Müller , Nico Scherf

Mirror descent (MD), a well-known first-order method in constrained convex optimization, has recently been shown as an important tool to analyze trust-region algorithms in reinforcement learning (RL). However, there remains a considerable…

Machine Learning · Computer Science 2021-06-08 Manan Tomar , Lior Shani , Yonathan Efroni , Mohammad Ghavamzadeh

Optimal transport (OT) defines a powerful framework to compare probability distributions in a geometrically faithful way. However, the practical impact of OT is still limited because of its computational burden. We propose a new class of…

Optimization and Control · Mathematics 2016-05-30 Genevay Aude , Marco Cuturi , Gabriel Peyré , Francis Bach

Policy gradient methods for Large Language Models optimize a policy $\pi_\theta$ via a surrogate objective computed from samples of a rollout policy $\pi_{\text{roll}}$. However, modern LLM-RL pipelines suffer from unavoidable…

Machine Learning · Computer Science 2026-03-02 Yingru Li , Jiacai Liu , Jiawei Xu , Yuxuan Tong , Ziniu Li , Qian Liu , Baoxiang Wang

Variational problems that involve Wasserstein distances and more generally optimal transport (OT) theory are playing an increasingly important role in data sciences. Such problems can be used to form an examplar measure out of various…

Machine Learning · Computer Science 2018-11-15 Marco Cuturi , Gabriel Peyré

Making sense of Wasserstein distances between discrete measures in high-dimensional settings remains a challenge. Recent work has advocated a two-step approach to improve robustness and facilitate the computation of optimal transport, using…

Machine Learning · Computer Science 2019-09-04 François-Pierre Paty , Marco Cuturi

Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators is poorly…

Statistics Theory · Mathematics 2021-07-20 Tianyi Lin , Zeyu Zheng , Elynn Y. Chen , Marco Cuturi , Michael I. Jordan