English
Related papers

Related papers: Robust First and Second-Order Differentiation for …

200 papers

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

The current best practice for computing optimal transport (OT) is via entropy regularization and Sinkhorn iterations. This algorithm runs in quadratic time as it requires the full pairwise cost matrix, which is prohibitively expensive for…

Machine Learning · Computer Science 2022-04-06 Johannes Gasteiger , Marten Lienen , Stephan Günnemann

We analyze two algorithms for approximating the general optimal transport (OT) distance between two discrete distributions of size $n$, up to accuracy $\varepsilon$. For the first algorithm, which is based on the celebrated Sinkhorn's…

Data Structures and Algorithms · Computer Science 2018-06-08 Pavel Dvurechensky , Alexander Gasnikov , Alexey Kroshnin

Optimal Transport (OT) based distances are powerful tools for machine learning to compare probability measures and manipulate them using OT maps. In this field, a setting of interest is semi-discrete OT, where the source measure $\mu$ is…

Efficient computation of the optimal transport distance between two distributions serves as an algorithm subroutine that empowers various applications. This paper develops a scalable first-order optimization-based method that computes…

Machine Learning · Computer Science 2024-06-21 Gen Li , Yanxi Chen , Yu Huang , Yuejie Chi , H. Vincent Poor , Yuxin Chen

The optimal transport (OT) problem is a classical optimization problem having the form of linear programming. Machine learning applications put forward new computational challenges in its solution. In particular, the OT problem defines a…

Optimization and Control · Mathematics 2022-10-25 Nazarii Tupitsa , Pavel Dvurechensky , Darina Dvinskikh , Alexander Gasnikov

This paper investigates the semi-discrete optimal transport (OT) problem with entropic regularization. We characterize the solution using a governing, well-posed ordinary differential equation (ODE). This naturally yields an algorithm to…

Numerical Analysis · Mathematics 2025-04-07 Luca Nenna , Daniyar Omarov , Brendan Pass

Entropic optimal transport (OT) and the Sinkhorn algorithm have made it practical for machine learning practitioners to perform the fundamental task of calculating transport distance between statistical distributions. In this work, we focus…

Optimization and Control · Mathematics 2024-03-11 Xun Tang , Holakou Rahmanian , Michael Shavlovsky , Kiran Koshy Thekumparampil , Tesi Xiao , Lexing Ying

Regularized optimal transport (OT) is now increasingly used as a loss or as a matching layer in neural networks. Entropy-regularized OT can be computed using the Sinkhorn algorithm but it leads to fully-dense transportation plans, meaning…

Machine Learning · Statistics 2023-04-17 Tianlin Liu , Joan Puigcerver , Mathieu Blondel

Unbalanced Optimal Transport (UOT) has emerged as a robust relaxation of standard Optimal Transport, particularly effective for handling outliers and mass variations. However, scalable algorithms for UOT, specifically those based on…

Optimization and Control · Mathematics 2026-02-12 Ferdinand Genans

We develop a fast and reliable method for solving large-scale optimal transport (OT) problems at an unprecedented combination of speed and accuracy. Built on the celebrated Douglas-Rachford splitting technique, our method tackles the…

Optimization and Control · Mathematics 2021-10-25 Vien V. Mai , Jacob Lindbäck , Mikael Johansson

Distributionally robust optimization (DRO) is a powerful technique to train robust models against data distribution shift. This paper aims to solve regularized nonconvex DRO problems, where the uncertainty set is modeled by a so-called…

Optimization and Control · Mathematics 2025-06-30 Yufeng Yang , Yi Zhou , Zhaosong Lu

While first-order optimization methods such as stochastic gradient descent (SGD) are popular in machine learning (ML), they come with well-known deficiencies, including relatively-slow convergence, sensitivity to the settings of…

Optimization and Control · Mathematics 2018-02-19 Peng Xu , Farbod Roosta-Khorasani , Michael W. Mahoney

This paper improves the state-of-the-art rate of a first-order algorithm for solving entropy regularized optimal transport. The resulting rate for approximating the optimal transport (OT) has been improved from…

Optimization and Control · Mathematics 2023-01-25 Yiling Luo , Yiling Xie , Xiaoming Huo

Optimal transport (OT) is a versatile framework for comparing probability measures, with many applications to statistics, machine learning, and applied mathematics. However, OT distances suffer from computational and statistical scalability…

Statistics Theory · Mathematics 2022-06-08 Ziv Goldfeld , Kengo Kato , Gabriel Rioux , Ritwik Sadhu

Optimal Transport (OT) distances are now routinely used as loss functions in ML tasks. Yet, computing OT distances between arbitrary (i.e. not necessarily discrete) probability distributions remains an open problem. This paper introduces a…

Optimization and Control · Mathematics 2020-07-03 Arthur Mensch , Gabriel Peyré

In this paper, we give a sharp analysis for Stochastic Gradient Descent (SGD) and prove that SGD is able to efficiently escape from saddle points and find an $(\epsilon, O(\epsilon^{0.5}))$-approximate second-order stationary point in…

Optimization and Control · Mathematics 2019-06-05 Cong Fang , Zhouchen Lin , Tong Zhang

Optimal Transport (OT) has recently emerged as a central tool in data sciences to compare in a geometrically faithful way point clouds and more generally probability distributions. The wide adoption of OT into existing data analysis and…

Machine Learning · Statistics 2023-01-18 Thibault Séjourné , Gabriel Peyré , François-Xavier Vialard

We present an algorithm for minimizing a sum of functions that combines the computational efficiency of stochastic gradient descent (SGD) with the second order curvature information leveraged by quasi-Newton methods. We unify these…

Machine Learning · Computer Science 2014-12-02 Jascha Sohl-Dickstein , Ben Poole , Surya Ganguli

The ability to compare two degenerate probability distributions (i.e. two probability distributions supported on two distinct low-dimensional manifolds living in a much higher-dimensional space) is a crucial problem arising in the…

Machine Learning · Statistics 2017-10-23 Aude Genevay , Gabriel Peyré , Marco Cuturi
‹ Prev 1 2 3 10 Next ›