English
Related papers

Related papers: Muon Dynamics as a Spectral Wasserstein Flow

200 papers

Suppose we are given two metric spaces and a family of continuous transformations from one to the other. Given a probability distribution on each of these two spaces - namely the source and the target measures - the Wasserstein alignment…

Probability · Mathematics 2025-03-11 Soumik Pal , Bodhisattva Sen , Ting-Kam Leonard Wong

Optimization lies at the core of modern deep learning, yet existing methods often face a fundamental trade-off between adapting to problem geometry and leveraging curvature utilization. Steepest descent algorithms adapt to different…

This article establishes the cutoff phenomenon in the Wasserstein distance for systems of nonlinear ordinary differential equations with a unique coercive stable fixed point subject to general additive Markovian noise in the limit of small…

Probability · Mathematics 2023-05-05 Gerardo Barrera , Michael A. Högele , Juan Carlos Pardo

We numerically investigate a mean-field Bayesian approach with the assistance of the Markov chain Monte Carlo method to estimate motion velocity fields and probabilistic models simultaneously in consecutive digital images described by…

Computer Vision and Pattern Recognition · Computer Science 2010-04-22 Yuya Inagaki , Jun-ichi Inoue

Consider a probability measure on a Hilbert space defined via its density with respect to a Gaussian. The purpose of this paper is to demonstrate that an appropriately defined Markov chain, which is reversible with respect to the measure in…

Statistics Theory · Mathematics 2014-04-21 Natesh S. Pillai , Andrew M. Stuart , Alexandre H. Thiery

Learning with symmetric positive definite (SPD) matrices has many applications in machine learning. Consequently, understanding the Riemannian geometry of SPD matrices has attracted much attention lately. A particular Riemannian geometry of…

Functional Analysis · Mathematics 2023-06-12 Andi Han , Bamdev Mishra , Pratik Jawanpuria , Junbin Gao

In this paper we bring together some of the key ideas and methods of two disparate fields of mathematical research, frame theory and optimal transport, using the methods of the second to answer questions posed in the first. In particular,…

Functional Analysis · Mathematics 2022-12-01 Clare Wickman , Kasso Okoudjou

We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows framework to learn stable Stochastic Differential Equations.…

Machine Learning · Computer Science 2020-10-27 Julen Urain , Michelle Ginesi , Davide Tateo , Jan Peters

Wasserstein gradient flow (WGF) is a common method to perform optimization over the space of probability measures. While WGF is guaranteed to converge to a first-order stationary point, for nonconvex functionals the converged solution does…

Optimization and Control · Mathematics 2025-09-23 Naoya Yamamoto , Juno Kim , Taiji Suzuki

In this work, we establish non-asymptotic convergence bounds for the Gauss-Newton method in training neural networks with smooth activations. In the underparameterized regime, the Gauss-Newton gradient flow in parameter space induces a…

Optimization and Control · Mathematics 2025-12-23 Semih Cayci

We consider $M/Ph/n+M$ queueing systems in steady state. We prove that the Wasserstein distance between the stationary distribution of the normalized system size process and that of a piecewise Ornstein-Uhlenbeck (OU) process is bounded by…

Probability · Mathematics 2015-12-01 Anton Braverman , J. G. Dai

Issued from Optimal Transport, the Wasserstein distance has gained importance in Machine Learning due to its appealing geometrical properties and the increasing availability of efficient approximations. In this work, we consider the problem…

Machine Learning · Statistics 2022-02-21 Guillaume Staerman , Pierre Laforgue , Pavlo Mozharovskyi , Florence d'Alché-Buc

This article presents a new class of distances between arbitrary nonnegative Radon measures inspired by optimal transport. These distances are defined by two equivalent alternative formulations: (i) a dynamic formulation defining the…

Optimization and Control · Mathematics 2019-02-12 Lenaic Chizat , Gabriel Peyré , Bernhard Schmitzer , François-Xavier Vialard

Many machine learning problems can be expressed as the optimization of some cost functional over a parametric family of probability distributions. It is often beneficial to solve such optimization problems using natural gradient methods.…

Machine Learning · Statistics 2020-02-14 Michael Arbel , Arthur Gretton , Wuchen Li , Guido Montufar

We present a computational framework for efficient learning, sampling, and distribution of general Bayesian posterior distributions. The framework leverages a machine learning approach for the construction of normalizing flows for the…

Nuclear Theory · Physics 2023-10-10 Yukari Yamauchi , Landon Buskirk , Pablo Giuliani , Kyle Godbey

Optimal Transport has sparked vivid interest in recent years, in particular thanks to the Wasserstein distance, which provides a geometrically sensible and intuitive way of comparing probability measures. For computational reasons, the…

Machine Learning · Computer Science 2024-03-19 Eloi Tanguy

Based on the manifold hypothesis, real-world data often lie on a low-dimensional manifold, while normalizing flows as a likelihood-based generative model are incapable of finding this manifold due to their structural constraints. So, one…

Machine Learning · Computer Science 2022-06-08 Seyedeh Fatemeh Razavi , Mohammad Mahdi Mehmanchi , Reshad Hosseini , Mostafa Tavassolipour

Wasserstein distributionally robust optimization (DRO) aims to find robust and generalizable solutions by hedging against data perturbations in Wasserstein distance. Despite its recent empirical success in operations research and machine…

Machine Learning · Computer Science 2022-05-03 Rui Gao

Probabilistic smoothing is a standard tool for global optimization, but existing methods rely on Gaussian kernels and specific transforms, often resulting in strong hyperparameter sensitivity and limited robustness. We propose a general…

Machine Learning · Computer Science 2026-05-27 Kukyoung Jang , Taehyun Cho , Junrui Zhang , Ping Xu , Kyungjae Lee

Recent results have shown that for two-layer fully connected neural networks, gradient flow converges to a global optimum in the infinite width limit, by making a connection between the mean field dynamics and the Wasserstein gradient flow.…

Optimization and Control · Mathematics 2020-07-16 Walid Krichene , Kenneth F. Caluya , Abhishek Halder
‹ Prev 1 8 9 10 Next ›