English
Related papers

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

200 papers

We introduce a new second order stochastic algorithm to estimate the entropically regularized optimal transport cost between two probability measures. The source measure can be arbitrary chosen, either absolutely continuous or discrete,…

Statistics Theory · Mathematics 2022-03-03 Bernard Bercu , Jérémie Bigot , Sébastien Gadat , Emilia Siviero

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein distance is replaced by…

Machine Learning · Statistics 2019-06-04 Giulia Luise , Alessandro Rudi , Massimiliano Pontil , Carlo Ciliberto

Optimal transport (OT) plays an essential role in various areas like machine learning and deep learning. However, computing discrete optimal transport plan for large scale problems with adequate accuracy and efficiency is still highly…

Machine Learning · Computer Science 2021-07-20 Dongsheng An , Na Lei , Xianfeng Gu

In this paper, we try to uncover the second-order essence of several first-order optimization methods. For Nesterov Accelerated Gradient, we rigorously prove that the algorithm makes use of the difference between past and current gradients,…

Machine Learning · Computer Science 2019-12-23 Yuzheng Hu , Licong Lin , Shange Tang

Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We propose to leverage the flexibility of neural networks to learn an approximate optimal transport map. More precisely, we present a new and…

Machine Learning · Computer Science 2022-07-06 Florentin Coeurdoux , Nicolas Dobigeon , Pierre Chainais

In machine learning and computer graphics, a fundamental task is the approximation of a probability density function through a well-dispersed collection of samples. Providing a formal metric for measuring the distance between probability…

Graphics · Computer Science 2024-02-28 Baptiste Genest , Nicolas Courty , David Coeurjolly

Stochastic gradient descent (SGD) is a prevalent optimization technique for large-scale distributed machine learning. While SGD computation can be efficiently divided between multiple machines, communication typically becomes a bottleneck…

Machine Learning · Computer Science 2021-05-24 Dmitrii Avdiukhin , Grigory Yaroslavtsev

We study the Unbalanced Optimal Transport (UOT) between two measures of possibly different masses with at most $n$ components, where the marginal constraints of standard Optimal Transport (OT) are relaxed via Kullback-Leibler divergence…

Optimization and Control · Mathematics 2024-01-09 Quang Minh Nguyen , Hoang H. Nguyen , Yi Zhou , Lam M. Nguyen

Optimal transport (OT) aims to find a map $T$ that transports mass from one probability measure to another while minimizing a cost function. Recently, neural OT solvers have gained popularity in high dimensional biological applications such…

Machine Learning · Computer Science 2025-05-20 Peter Chen , Yue Xie , Qingpeng Zhang

\emph{Optimal Transport} (OT) has emerged as an important computational tool in machine learning and computer vision, providing a geometrical framework for studying probability measures. OT unfortunately suffers from the curse of…

Machine Learning · Computer Science 2021-02-08 Anton Mallasto

Optimal Transport (OT) has attracted significant interest in the machine learning community, not only for its ability to define meaningful distances between probability distributions -- such as the Wasserstein distance -- but also for its…

Machine Learning · Computer Science 2025-11-04 Laetitia Chapel , Romain Tavenard , Samuel Vaiter

A novel dynamical inertial Newton system, which is called Hessian-driven Nesterov accelerated gradient (H-NAG) flow is proposed. Convergence of the continuous trajectory are established via tailored Lyapunov function, and new first-order…

Optimization and Control · Mathematics 2019-12-25 Long Chen , Hao Luo

Optimal transport (OT) and maximum mean discrepancies (MMD) are now routinely used in machine learning to compare probability measures. We focus in this paper on \emph{Sinkhorn divergences} (SDs), a regularized variant of OT distances which…

Statistics Theory · Mathematics 2019-10-16 Aude Genevay , Lénaic Chizat , Francis Bach , Marco Cuturi , Gabriel Peyré

This paper presents a unified framework for smooth convex regularization of discrete optimal transport problems. In this context, the regularized optimal transport turns out to be equivalent to a matrix nearness problem with respect to…

Machine Learning · Statistics 2018-07-17 Arnaud Dessein , Nicolas Papadakis , Jean-Luc Rouas

In this paper, we propose objective-function-free (OFF) variants of the proximal Newton method for nonconvex composite optimization problems and the regularized Newton method for unconstrained optimization problems, respectively, using…

Optimization and Control · Mathematics 2026-05-19 Hong Zhu

Entropic regularization is quickly emerging as a new standard in optimal transport (OT). It enables to cast the OT computation as a differentiable and unconstrained convex optimization problem, which can be efficiently solved using the…

Machine Learning · Statistics 2018-02-21 Mathieu Blondel , Vivien Seguy , Antoine Rolet

We investigate the problem of finding second-order stationary points (SOSP) in differentially private (DP) stochastic non-convex optimization. Existing methods suffer from two key limitations: (i) inaccurate convergence error rate due to…

Machine Learning · Computer Science 2026-01-21 Youming Tao , Zuyuan Zhang , Dongxiao Yu , Xiuzhen Cheng , Falko Dressler , Di Wang

Following early work on Hessian-free methods for deep learning, we study a stochastic generalized Gauss-Newton method (SGN) for training DNNs. SGN is a second-order optimization method, with efficient iterations, that we demonstrate to…

Machine Learning · Computer Science 2020-06-11 Matilde Gargiani , Andrea Zanelli , Moritz Diehl , Frank Hutter

Optimal transport (OT) serves as a natural framework for comparing probability measures, with applications in statistics, machine learning, and applied mathematics. Alas, statistical estimation and exact computation of the OT distances…

Statistics Theory · Mathematics 2024-05-14 Tao Wang , Ziv Goldfeld

Optimal transport (OT) is a powerful framework to compare probability measures, a fundamental task in many statistical and machine learning problems. Substantial advances have been made in designing OT variants which are either…

Machine Learning · Computer Science 2025-02-04 Clément Bonet , Kimia Nadjahi , Thibault Séjourné , Kilian Fatras , Nicolas Courty