English
Related papers

Related papers: Properties and limitations of geometric tempering …

200 papers

Under general assumptions on the target distribution $p^\star$, we establish a sharp Lipschitz regularity theory for flow-matching vector fields and diffusion-model scores, with optimal dependence on time and dimension. As applications, we…

Statistics Theory · Mathematics 2026-04-08 Arthur Stéphanovitch

Many large-scale and distributed optimization problems can be brought into a composite form in which the objective function is given by the sum of a smooth term and a nonsmooth regularizer. Such problems can be solved via a proximal…

Optimization and Control · Mathematics 2020-06-26 Sepideh Hassan-Moghaddam , Mihailo R. Jovanović

We develop in this paper a new regularized flow dynamic approach to construct efficient numerical schemes for Wasserstein gradient flows in Lagrangian coordinates. Instead of approximating the Wasserstein distance which needs to solve…

Numerical Analysis · Mathematics 2024-06-24 Qing Cheng , Qianqian Liu , Wenbin Chen , Jie Shen

One of the most popular approaches for solving total variation-regularized optimization problems in the space of measures are Particle Gradient Flows (PGFs). These restrict the problem to linear combinations of Dirac deltas and then perform…

Optimization and Control · Mathematics 2026-03-31 Christian Amend , Marcello Carioni , Konstantinos Zemas

We provide a general bound on the Wasserstein distance between two arbitrary distributions of sequences of Bernoulli random variables. The bound is in terms of a mixing quantity for the Glauber dynamics of one of the sequences, and a simple…

Probability · Mathematics 2018-10-12 Gesine Reinert , Nathan Ross

The Kullback-Leibler (KL) divergence plays a central role in probabilistic machine learning, where it commonly serves as the canonical loss function. Optimization in such settings is often performed over the probability simplex, where the…

Machine Learning · Computer Science 2025-07-31 Adwait Datar , Nihat Ay

Gaussian mixture models form a flexible and expressive parametric family of distributions that has found applications in a wide variety of applications. Unfortunately, fitting these models to data is a notoriously hard problem from a…

Statistics Theory · Mathematics 2023-01-05 Yuling Yan , Kaizheng Wang , Philippe Rigollet

While gradient-based discrete samplers are effective in sampling from complex distributions, they are susceptible to getting trapped in local minima, particularly in high-dimensional, multimodal discrete distributions, owing to the…

Machine Learning · Statistics 2025-05-21 Luxu Liang , Yuhang Jia , Feng Zhou

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

Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely…

Machine Learning · Statistics 2023-02-14 A. Duncan , N. Nuesken , L. Szpruch

We study discretizations of Hamiltonian systems on the probability density manifold equipped with the $L^2$-Wasserstein metric. Based on discrete optimal transport theory, several Hamiltonian systems on graph (lattice) with different…

Numerical Analysis · Mathematics 2020-06-17 Jianbo Cui , Luca Dieci , Haomin Zhou

This paper is a strongly geometrical approach to the Fisher distance, which is a measure of dissimilarity between two probability distribution functions. The Fisher distance, as well as other divergence measures, are also used in many…

Methodology · Statistics 2014-01-13 Sueli I. R. Costa , Sandra A. Santos , João E. Strapasson

The aim of this paper is to address the challenge of gradual domain adaptation within a class of manifold-constrained data distributions. In particular, we consider a sequence of $T\ge2$ data distributions $P_1,\ldots,P_T$ undergoing a…

Accelerated gradient methods are the cornerstones of large-scale, data-driven optimization problems that arise naturally in machine learning and other fields concerning data analysis. We introduce a gradient-based optimization framework for…

Optimization and Control · Mathematics 2022-03-22 Param Budhraja , Mayank Baranwal , Kunal Garg , Ashish Hota

This paper studies the numerical approximation of evolution equations by nonlinear parametrizations $u(t)=\Phi(\param(t))$ with time-dependent parameters $\param(t)$, which are to be determined in the computation. The motivation comes from…

Numerical Analysis · Mathematics 2026-03-23 Michael Feischl , Caroline Lasser , Christian Lubich , Jörg Nick

We study the Wasserstein gradient flow of the Sinkhorn divergence when both the source and the target are Gaussian distributions. We prove the existence of a flow that stays in the class of Gaussian distributions, and is unique in the…

Analysis of PDEs · Mathematics 2026-02-20 Mathis Hardion , Théo Lacombe

Application of the replica exchange (i.e., parallel tempering) technique to Langevin Monte Carlo algorithms, especially stochastic gradient Langevin dynamics (SGLD), has scored great success in non-convex learning problems, but one…

Numerical Analysis · Mathematics 2023-01-06 Guanxun Li , Guang Lin , Zecheng Zhang , Quan Zhou

We design strategies in nonlinear geometric analysis to temper the effects of adversarial learning for sufficiently smooth data of numerical method-type dynamics in encoder-decoder methods, variational and deterministic, through the use of…

Numerical Analysis · Mathematics 2026-05-29 Andrew Gracyk

Generative modeling over discrete data has recently seen numerous success stories, with applications spanning language modeling, biological sequence design, and graph-structured molecular data. The predominant generative modeling paradigm…

Machine Learning · Computer Science 2024-11-01 Oscar Davis , Samuel Kessler , Mircea Petrache , İsmail İlkan Ceylan , Michael Bronstein , Avishek Joey Bose

We analyze the gradient flow of a potential energy in the space of probability measures when we substitute the optimal transport geometry with a geometry based on Sinkhorn divergences, a debiased version of entropic optimal transport. This…

Analysis of PDEs · Mathematics 2025-11-19 Mathis Hardion , Hugo Lavenant