English
Related papers

Related papers: Optimizing Functionals on the Space of Probabiliti…

200 papers

We consider a class of optimization problems on the space of probability measures motivated by the mean-field approach to studying neural networks. Such problems can be solved by constructing continuous-time gradient flows that converge to…

Optimization and Control · Mathematics 2026-02-18 Petra Lazić , Linshan Liu , Mateusz B. Majka

The incremental gradient method is a prominent algorithm for minimizing a finite sum of smooth convex functions, used in many contexts including large-scale data processing applications and distributed optimization over networks. It is a…

Optimization and Control · Mathematics 2022-02-09 Mert Gürbüzbalaban , Asuman Ozdaglar , Pablo Parrilo

Physics informed neural networks (PINNs) represent a very popular class of neural solvers for partial differential equations. In practice, one often employs stochastic gradient descent type algorithms to train the neural network. Therefore,…

Machine Learning · Computer Science 2025-09-01 Bangti Jin , Longjun Wu

This is an expository paper on the theory of gradient flows, and in particular of those PDEs which can be interpreted as gradient flows for the Wasserstein metric on the space of probability measures (a distance induced by optimal…

Analysis of PDEs · Mathematics 2016-09-14 Filippo Santambrogio

Entropic optimal transport problems are regularized versions of optimal transport problems. These models play an increasingly important role in machine learning and generative modelling. For finite spaces, these problems are commonly solved…

Machine Learning · Statistics 2025-12-30 O. Deniz Akyildiz , Pierre Del Moral , Joaquín Miguez

Applications such as adversarially robust training and Wasserstein Distributionally Robust Optimization (WDRO) can be naturally formulated as min-sum-max optimization problems. While this formulation can be rewritten as an equivalent…

Optimization and Control · Mathematics 2025-02-26 Wei Liu , Muhammad Khan , Gabriel Mancino-Ball , Yangyang Xu

We present a novel communication-efficient Newton-type algorithm for finite-sum optimization over a distributed computing environment. Our method, named DINO, overcomes both theoretical and practical shortcomings of similar existing…

Optimization and Control · Mathematics 2020-06-09 Rixon Crane , Fred Roosta

The Wasserstein gradient flow structure of the PDE system governing multiphase flows in porous media was recently highlighted in [C. Canc\`es, T. O. Gallou\"et, and L. Monsaingeon, {\it Anal. PDE} 10(8):1845--1876, 2017]. The model can thus…

Numerical Analysis · Mathematics 2018-07-23 Clément Cancès , Thomas O. Gallouët , Maxime Laborde , Léonard Monsaingeon

A novel inner approximation algorithm is proposed for dynamic optimization problems to ensure strict satisfaction of path constraints. Distinct from traditional methods relying on interval analysis, the proposed algorithm leverages the…

Optimization and Control · Mathematics 2026-02-10 Yuan Chang , Lizhong Jiang , Tai-Fang Li , Jun Fu

We consider Monge-Kantorovich optimal transport problems on $\mathbb{R}^d$, $d\ge 1$, with a convex cost function given by the cumulant generating function of a probability measure. Examples include the Wasserstein-2 transport whose cost…

Probability · Mathematics 2017-08-29 Soumik Pal

Variational inference (VI) can be cast as an optimization problem in which the variational parameters are tuned to closely align a variational distribution with the true posterior. The optimization task can be approached through vanilla…

Machine Learning · Computer Science 2025-04-24 Dai Hai Nguyen , Tetsuya Sakurai , Hiroshi Mamitsuka

We introduce a new second-order inertial optimization method for machine learning called INNA. It exploits the geometry of the loss function while only requiring stochastic approximations of the function values and the generalized…

Machine Learning · Computer Science 2021-08-17 Camille Castera , Jérôme Bolte , Cédric Févotte , Edouard Pauwels

By building upon the recent theory that established the connection between implicit generative modeling (IGM) and optimal transport, in this study, we propose a novel parameter-free algorithm for learning the underlying distributions of…

Machine Learning · Statistics 2019-06-12 Antoine Liutkus , Umut Şimşekli , Szymon Majewski , Alain Durmus , Fabian-Robert Stöter

Optimal Mass Transport (OMT) is a well studied problem with a variety of applications in a diverse set of fields ranging from Physics to Computer Vision and in particular Statistics and Data Science. Since the original formulation of Monge…

Machine Learning · Computer Science 2021-10-26 Amanpreet Singh , Martin Bauer , Sarang Joshi

In this paper, we consider optimizing a smooth, convex, lower semicontinuous function in Riemannian space with constraints. To solve the problem, we first convert it to a dual problem and then propose a general primal-dual algorithm to…

Machine Learning · Computer Science 2020-05-20 Shijun Wang , Baocheng Zhu , Lintao Ma , Yuan Qi

We study a variant of the dynamical optimal transport problem in which the energy to be minimised is modulated by the covariance matrix of the distribution. Such transport metrics arise naturally in mean-field limits of certain ensemble…

Analysis of PDEs · Mathematics 2024-12-23 Martin Burger , Matthias Erbar , Franca Hoffmann , Daniel Matthes , André Schlichting

In this paper, a globally convergent Newton-type proximal gradient method is developed for composite multi-objective optimization problems where each objective function can be represented as the sum of a smooth function and a nonsmooth…

Optimization and Control · Mathematics 2024-10-25 Md Abu Talhamainuddin Ansary

To solve convex optimization problems with a noisy gradient input, we analyze the global behavior of subgradient-like flows under stochastic errors. The objective function is composite, being equal to the sum of two convex functions, one…

Optimization and Control · Mathematics 2025-06-05 Rodrigo Maulen-Soto , Jalal Fadili , Hedy Attouch

The acceleration of gradient-based optimization methods is a subject of significant practical and theoretical importance, particularly within machine learning applications. While much attention has been directed towards optimizing within…

Optimization and Control · Mathematics 2024-11-12 Shi Chen , Qin Li , Oliver Tse , Stephen J. Wright

This paper introduces the Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO) algorithm into reinforcement learning. The Hamilton-Jacobi-Bellman (HJB) equation is used in control theory to evaluate the optimality of the value…

Machine Learning · Computer Science 2023-02-02 Amartya Mukherjee , Jun Liu