English
Related papers

Related papers: Transport map unadjusted Langevin algorithms: lear…

200 papers

This paper considers the problem of distributed optimization over time-varying graphs. For the case of undirected graphs, we introduce a distributed algorithm, referred to as DIGing, based on a combination of a distributed inexact gradient…

Optimization and Control · Mathematics 2017-03-21 Angelia Nedich , Alex Olshevsky , Wei Shi

Computing optimal transport maps between high-dimensional and continuous distributions is a challenging problem in optimal transport (OT). Generative adversarial networks (GANs) are powerful generative models which have been successfully…

Machine Learning · Computer Science 2019-06-25 Jacob Leygonie , Jennifer She , Amjad Almahairi , Sai Rajeswar , Aaron Courville

Langevin Dynamics is a Stochastic Differential Equation (SDE) central to sampling and generative modeling and is implemented via time discretization. Langevin Monte Carlo (LMC), based on the Euler-Maruyama discretization, is the simplest…

Machine Learning · Computer Science 2025-10-10 Saravanan Kandasamy , Dheeraj Nagaraj

We propose a new discretization of the mirror-Langevin diffusion and give a crisp proof of its convergence. Our analysis uses relative convexity/smoothness and self-concordance, ideas which originated in convex optimization, together with a…

Statistics Theory · Mathematics 2021-10-26 Kwangjun Ahn , Sinho Chewi

This work studies an explicit embedding of the set of probability measures into a Hilbert space, defined using optimal transport maps from a reference probability density. This embedding linearizes to some extent the 2-Wasserstein space,…

Machine Learning · Statistics 2022-05-05 Quentin Mérigot , Alex Delalande , Frédéric Chazal

In this paper, we consider the underdamped Langevin diffusion (ULD) and propose a numerical approximation using its associated ordinary differential equation (ODE). When used as a Markov Chain Monte Carlo (MCMC) algorithm, we show that the…

Numerical Analysis · Mathematics 2021-01-26 James Foster , Terry Lyons , Harald Oberhauser

A canonical algorithm for log-concave sampling is the Langevin Algorithm, aka the Langevin Diffusion run with some discretization stepsize $\eta > 0$. This discretization leads the Langevin Algorithm to have a stationary distribution…

Machine Learning · Statistics 2024-10-22 Jason M. Altschuler , Kunal Talwar

In order to solve tasks like uncertainty quantification or hypothesis tests in Bayesian imaging inverse problems, we often have to draw samples from the arising posterior distribution. For the usually log-concave but high-dimensional…

Computation · Statistics 2025-01-23 Matthias J. Ehrhardt , Lorenz Kuger , Carola-Bibiane Schönlieb

Many causal and structural parameters in economics can be identified and estimated by computing the value of an optimization program over all distributions consistent with the model and the data. Existing tools apply when the data is…

Econometrics · Economics 2025-07-31 Andrei Voronin

Sampling from high-dimensional distributions is a fundamental problem in statistical research and practice. However, great challenges emerge when the target density function is unnormalized and contains isolated modes. We tackle this…

Methodology · Statistics 2023-04-11 Yixuan Qiu , Xiao Wang

We study the unbalanced optimal transport (UOT) problem, where the marginal constraints are enforced using Maximum Mean Discrepancy (MMD) regularization. Our work is motivated by the observation that the literature on UOT is focused on…

Machine Learning · Computer Science 2024-02-01 Piyushi Manupriya , J. Saketha Nath , Pratik Jawanpuria

Approximate Bayesian inference estimates descriptors of an intractable target distribution - in essence, an optimization problem within a family of distributions. For example, Langevin dynamics (LD) extracts asymptotically exact samples…

Machine Learning · Statistics 2021-10-11 Zheyang Shen , Markus Heinonen , Samuel Kaski

Optimal Transport has received much attention in Machine Learning as it allows to compare probability distributions by exploiting the geometry of the underlying space. However, in its original formulation, solving this problem suffers from…

Machine Learning · Computer Science 2023-11-27 Clément Bonet

We sample from a given target distribution by constructing a neural network which maps samples from a simple reference, e.g. the standard normal distribution, to samples from the target. To that end, we propose using a neural network…

Machine Learning · Computer Science 2024-12-11 Charles Miranda , Janina Schütte , David Sommer , Martin Eigel

Stochastic gradient MCMC methods, such as stochastic gradient Langevin dynamics (SGLD), employ fast but noisy gradient estimates to enable large-scale posterior sampling. Although we can easily extend SGLD to distributed settings, it…

Machine Learning · Statistics 2021-06-16 Khaoula El Mekkaoui , Diego Mesquita , Paul Blomstedt , Samuel Kaski

Data-driven modeling of non-Markovian dynamics is a recent topic of research with applications in many fields such as climate research, molecular dynamics, biophysics, or wind power modeling. In the frequently used standard Langevin…

Data Analysis, Statistics and Probability · Physics 2022-07-22 Clemens Willers , Oliver Kamps

Dynamical systems often exhibit the emergence of long-lived coherent sets, which are regions in state space that keep their geometric integrity to a high extent and thus play an important role in transport. In this article, we provide a…

Dynamical Systems · Mathematics 2017-04-05 Ralf Banisch , Péter Koltai

We introduce a constructive framework to learn effective Langevin equations from stationary time series. Unlike conventional approaches that require iterative calibration to match target statistics, our construction guarantees the observed…

Chaotic Dynamics · Physics 2026-02-16 Ludovico Theo Giorgini

We investigate the theoretical properties of general diffusion (interpolation) paths and their Langevin Monte Carlo implementation, referred to as diffusion annealed Langevin Monte Carlo (DALMC), under weak conditions on the data…

Machine Learning · Statistics 2025-02-14 Paula Cordero-Encinar , O. Deniz Akyildiz , Andrew B. Duncan

The Langevin Dynamics (LD), which aims to sample from a probability distribution using its score function, has been widely used for analyzing and developing score-based generative modeling algorithms. While the convergence behavior of LD in…

Machine Learning · Computer Science 2025-06-11 Xiwei Cheng , Kexin Fu , Farzan Farnia