中文
相关论文

相关论文: Sinkhorn Algorithm as a Special Case of Stochastic…

200 篇论文

Many problems in machine learning can be formulated as optimizing a convex functional over a vector space of measures. This paper studies the convergence of the mirror descent algorithm in this infinite-dimensional setting. Defining Bregman…

最优化与控制 · 数学 2022-10-12 Pierre-Cyril Aubin-Frankowski , Anna Korba , Flavien Léger

We present a new perspective on the popular Sinkhorn algorithm, showing that it can be seen as a Bregman gradient descent (mirror descent) of a relative entropy (Kullback-Leibler divergence). This viewpoint implies a new sublinear…

最优化与控制 · 数学 2020-06-11 Flavien Léger

Many problems in machine learning can be formulated as solving entropy-regularized optimal transport on the space of probability measures. The canonical approach involves the Sinkhorn iterates, renowned for their rich mathematical…

机器学习 · 计算机科学 2023-11-29 Mohammad Reza Karimi , Ya-Ping Hsieh , Andreas Krause

In this paper, we analyze the mirror descent algorithm for non-smooth optimization problems in which the objective function is relatively strongly convex, without relying on the standard Lipschitz continuity assumption commonly used in the…

最优化与控制 · 数学 2026-03-03 Mohammad S. Alkousa , Fedor S. Stonyakin

Based on the ideas of arXiv:1710.06612, we consider the problem of minimization of the Holder-continuous non-smooth functional $f$ with non-positive convex (generally, non-smooth) Lipschitz-continuous functional constraint. We propose some…

最优化与控制 · 数学 2022-01-03 Fedor Stonyakin , Alexey Stepanov , Alexander Gasnikov , Alexander Titov

This paper addresses the problem of approximating an unknown probability distribution with density $f$ -- which can only be evaluated up to an unknown scaling factor -- with the help of a sequential algorithm that produces at each iteration…

统计理论 · 数学 2024-09-23 Pascal Bianchi , Bernard Delyon , Victor Priser , François Portier

We study stochastic convex optimization under infinite noise variance. Specifically, when the stochastic gradient is unbiased and has uniformly bounded $(1+\kappa)$-th moment, for some $\kappa \in (0,1]$, we quantify the convergence rate of…

This paper is devoted to a new modification of a recently proposed adaptive stochastic mirror descent algorithm for constrained convex optimization problems in the case of several convex functional constraints. Algorithms, standard and its…

最优化与控制 · 数学 2020-01-22 Mohammad S. Alkousa

The paper is devoted to a special Mirror Descent algorithm for problems of convex minimization with functional constraints. The objective function may not satisfy the Lipschitz condition, but it must necessarily have the Lipshitz-continuous…

最优化与控制 · 数学 2018-04-17 Fedor S. Stonyakin , Alexander A. Titov

In this paper some adaptive mirror descent algorithms for problems of minimization convex objective functional with several convex Lipschitz (generally, non-smooth) functional constraints are considered. It is shown that the methods are…

最优化与控制 · 数学 2018-12-20 F. S. Stonyakin , M . S. Alkousa , A. A. Titov

The usual approach to developing and analyzing first-order methods for non-smooth (stochastic or deterministic) convex optimization assumes that the objective function is uniformly Lipschitz continuous with parameter $M_f$. However, in many…

最优化与控制 · 数学 2018-08-15 Haihao Lu

In this work, we develop a collection of novel methods for the entropic-regularised optimal transport problem, which are inspired by existing mirror descent interpretations of the Sinkhorn algorithm used for solving this problem. These are…

最优化与控制 · 数学 2025-07-17 Vishwak Srinivasan , Qijia Jiang

Smoothness is crucial for attaining fast rates in first-order optimization. However, many optimization problems in modern machine learning involve non-smooth objectives. Recent studies relax the smoothness assumption by allowing the…

最优化与控制 · 数学 2026-02-11 Dingzhi Yu , Wei Jiang , Hongyi Tao , Yuanyu Wan , Lijun Zhang

We consider distributed optimization with smooth convex objective functions defined on an undirected connected graph. Inspired by mirror descent mehod and RLC circuits, we propose a novel distributed mirror descent method. Compared with…

最优化与控制 · 数学 2020-02-25 Yue Yu , Behçet Açıkmeşe

Optimal transport is an important tool in machine learning, allowing to capture geometric properties of the data through a linear program on transport polytopes. We present a single-loop optimization algorithm for minimizing general convex…

机器学习 · 计算机科学 2023-06-21 Marin Ballu , Quentin Berthet

We introduce in this paper a novel strategy for efficiently approximating the Sinkhorn distance between two discrete measures. After identifying neglectable components of the dual solution of the regularized Sinkhorn problem, we propose to…

机器学习 · 统计学 2020-01-22 Mokhtar Z. Alaya , Maxime Bérar , Gilles Gasso , Alain Rakotomamonjy

Saddle point problems, ubiquitous in optimization, extend beyond game theory to diverse domains like power networks and reinforcement learning. This paper presents novel approaches to tackle saddle point problem, with a focus on…

最优化与控制 · 数学 2024-04-09 Anik Kumar Paul , Arun D Mahindrakar , Rachel K Kalaimani

We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport…

最优化与控制 · 数学 2025-03-27 Jie Wang , Rui Gao , Yao Xie

We consider centralized and distributed mirror descent algorithms over a finite-dimensional Hilbert space, and prove that the problem variables converge to an optimizer of a possibly nonsmooth function when the step sizes are square…

最优化与控制 · 数学 2018-05-07 Thinh T. Doan , Subhonmesh Bose , D. Hoa Nguyen , Carolyn L. Beck

We consider the problem of minimization of a convex function on a simple set with convex non-smooth inequality constraint and describe first-order methods to solve such problems in different situations: smooth or non-smooth objective…

‹ 上一页 1 2 3 10 下一页 ›