English
Related papers

Related papers: Trust Region Policy Optimization with Optimal Tran…

200 papers

We propose a fundamental metric for measuring the distance between two distributions. This metric, referred to as the decision-focused (DF) divergence, is tailored to stochastic linear optimization problems in which the objective…

Statistics Theory · Mathematics 2026-02-04 Suhan Liu , Mo Liu

Obtaining solutions to Optimal Transportation (OT) problems is typically intractable when the marginal spaces are continuous. Recent research has focused on approximating continuous solutions with discretization methods based on i.i.d.…

Optimization and Control · Mathematics 2021-02-17 Junqi Wang , Pei Wang , Patrick Shafto

Collaborative learning has recently achieved very significant results. It still suffers, however, from several issues, including the type of information that needs to be exchanged, the criteria for stopping and how to choose the right…

Machine Learning · Computer Science 2021-03-29 Fatima Ezzahraa Ben Bouazza , Younès Bennani

We develop a discrete optimal transport framework for analyzing simulated annealing algorithms on finite state spaces. Building on the discrete Wasserstein metric introduced by Maas (J. Funct. Anal., 2011), we define a generalized discrete…

Data Structures and Algorithms · Computer Science 2026-05-08 Yuchen He , Tianhui Jiang , Sihan Wang , Chihao Zhang

We propose Orthogonalized Policy Optimization (OPO), a principled framework for large language model alignment derived from optimization in the Hilbert function space L2(pi_k). Lifting policy updates from the probability simplex into…

Machine Learning · Computer Science 2026-02-26 Wang Zixian

We study finite-sample statistical performance guarantees for distributionally robust optimization (DRO) with optimal transport (OT) and OT-regularized divergence model neighborhoods. Specifically, we derive concentration inequalities for…

Machine Learning · Statistics 2026-03-31 Jeremiah Birrell , Xiaoxi Shen

Bayesian Optimization (BO) is a popular framework for optimizing black-box functions. Despite its effectiveness, BO is often inefficient for high-dimensional problems due to the exponential growth of the search space, heterogeneity of the…

Optimization and Control · Mathematics 2026-05-08 Sourav Das , Debjani Chakraborty , Pabitra Mitra

Optimal transport has gained significant attention in recent years due to its effectiveness in deep learning and computer vision. Its descendant metric, the Wasserstein distance, has been particularly successful in measuring distribution…

Optimization and Control · Mathematics 2025-02-18 Kaiwen Shi

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Machine Learning · Computer Science 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

Comparing time series in a principled manner requires capturing both temporal alignment and distributional similarity of features. Optimal transport (OT) has recently emerged as a powerful tool for this task, but existing OT-based…

Optimization and Control · Mathematics 2025-12-29 Thai P. D. Nguyen , Hong T. M. Chu , Kim-Chuan Toh

Discriminating between distributions is an important problem in a number of scientific fields. This motivated the introduction of Linear Optimal Transportation (LOT), which embeds the space of distributions into an $L^2$-space. The…

Machine Learning · Statistics 2021-05-27 Caroline Moosmüller , Alexander Cloninger

Modelling bounded rational decision-making through information constrained processing provides a principled approach for representing departures from rationality within a reinforcement learning framework, while still treating…

Machine Learning · Computer Science 2025-06-02 Benjamin Patrick Evans , Leo Ardon , Sumitra Ganesh

We study the problem of robust distribution estimation under the Wasserstein distance, a popular discrepancy measure between probability distributions rooted in optimal transport (OT) theory. Given $n$ samples from an unknown distribution…

Machine Learning · Statistics 2024-09-25 Sloan Nietert , Rachel Cummings , Ziv Goldfeld

The effects of treatments are often heterogeneous, depending on the observable characteristics, and it is necessary to exploit such heterogeneity to devise individualized treatment rules (ITRs). Existing estimation methods of such ITRs…

Econometrics · Economics 2022-08-09 Daido Kido

We present Group Orthogonalized Policy Optimization (GOPO), a new alignment algorithm for large language models derived from the geometry of Hilbert function spaces. Instead of optimizing on the probability simplex and inheriting the…

Machine Learning · Computer Science 2026-02-26 Wang Zixian

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of…

Machine Learning · Computer Science 2020-06-19 Yonathan Efroni , Lior Shani , Aviv Rosenberg , Shie Mannor

Group Relative Policy Optimization (GRPO) performs coarse-grained credit assignment in reinforcement learning with verifiable rewards (RLVR) by assigning the same advantage to all tokens in a rollout. Process reward models can provide…

Computation and Language · Computer Science 2026-04-28 Xinzhu Chen , Wei He , Huichuan Fan , Wenzhe Niu , Zhongxiang Sun , Xuanru Wang , Jiuchong Gao , Jinghua Hao , Renqing He , Weijie Yu

The notion of entropy-regularized optimal transport, also known as Sinkhorn divergence, has recently gained popularity in machine learning and statistics, as it makes feasible the use of smoothed optimal transportation distances for data…

Statistics Theory · Mathematics 2019-11-05 Jérémie Bigot , Elsa Cazelles , Nicolas Papadakis

Policy optimization (PO) algorithms are used to refine Large Language Models for complex, multi-step reasoning. Current state-of-the-art pipelines enforce a strict think-then-answer format to elicit chain-of-thought (CoT); however, the…

Computation and Language · Computer Science 2025-10-28 Debdeep Sanyal , Aakash Sen Sharma , Dhruv Kumar , Saurabh Deshpande , Murari Mandal

How should researchers select experimental sites when the deployment population differs from observed data? I formulate the problem of experimental site selection as an optimal transport problem, developing methods to minimize downstream…

Methodology · Statistics 2025-11-07 Adam Bouyamourn