English
Related papers

Related papers: Tamed Langevin sampling under weaker conditions

200 papers

Drawing from the theory of stochastic differential equations, we introduce a novel sampling method for known distributions and a new algorithm for diffusion generative models with unknown distributions. Our approach is inspired by the…

Statistics Theory · Mathematics 2024-07-12 Xicheng Zhang

Discrete time analogues of ergodic stochastic differential equations (SDEs) are one of the most popular and flexible tools for sampling high-dimensional probability measures. Non-asymptotic analysis in the $L^2$ Wasserstein distance of…

Probability · Mathematics 2019-10-11 Mateusz B. Majka , Aleksandar Mijatović , Lukasz Szpruch

Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications. In this paper, we introduce a novel analysis of the classical…

Machine Learning · Computer Science 2023-04-11 Rattana Pukdee , Dylan Sam , Maria-Florina Balcan , Pradeep Ravikumar

During recent years the interest of optimization and machine learning communities in high-probability convergence of stochastic optimization methods has been growing. One of the main reasons for this is that high-probability complexity…

In this paper, we are concerned with a non-asymptotic analysis of sampling algorithms used in nonconvex optimization. In particular, we obtain non-asymptotic estimates in Wasserstein-1 and Wasserstein-2 distances for a popular class of…

Statistics Theory · Mathematics 2022-10-17 Ying Zhang , Ömer Deniz Akyildiz , Theodoros Damoulas , Sotirios Sabanis

An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two popular methods are (1) Sequential Monte Carlo (SMC), where…

Machine Learning · Statistics 2025-09-09 Junhua Chen , Lorenz Richter , Julius Berner , Denis Blessing , Gerhard Neumann , Anima Anandkumar

Deep generative models hold great promise for representing complex physical systems, but their deployment is currently limited by the lack of guarantees on the physical plausibility of the generated outputs. Ensuring that known physical…

Machine Learning · Computer Science 2026-03-13 Matthieu Blanke , Yongquan Qu , Sara Shamekh , Pierre Gentine

Langevin Monte Carlo (LMC) and its stochastic gradient versions are powerful algorithms for sampling from complex high-dimensional distributions. To sample from a distribution with density $\pi(\theta)\propto \exp(-U(\theta)) $, LMC…

Computation · Statistics 2023-09-25 Sifan Liu

In this paper, we propose two new algorithms, namely, aHOLA and aHOLLA, to sample from high-dimensional target distributions with possibly super-linearly growing potentials. We establish non-asymptotic convergence bounds for aHOLA in…

Statistics Theory · Mathematics 2025-08-11 Ariel Neufeld , Ying Zhang

Distribution alignment has many applications in deep learning, including domain adaptation and unsupervised image-to-image translation. Most prior work on unsupervised distribution alignment relies either on minimizing simple non-parametric…

Machine Learning · Computer Science 2020-10-27 Ben Usman , Avneesh Sud , Nick Dufour , Kate Saenko

The kinetic Langevin dynamics finds diverse applications in various disciplines such as molecular dynamics and Hamiltonian Monte Carlo sampling. In this paper, a novel splitting scalar auxiliary variable (SSAV) scheme is proposed for the…

Numerical Analysis · Mathematics 2025-09-05 Lei Dai , Yingsong Jiang , Xiaojie Wang

This paper proposes a new sampling scheme based on Langevin dynamics that is applicable within pseudo-marginal and particle Markov chain Monte Carlo algorithms. We investigate this algorithm's theoretical properties under standard…

Methodology · Statistics 2016-05-30 Christopher Nemeth , Chris Sherlock , Paul Fearnhead

We study the variable metric forward-backward splitting algorithm for convex minimization problems without the standard assumption of the Lipschitz continuity of the gradient. In this setting, we prove that, by requiring only mild…

Optimization and Control · Mathematics 2017-05-02 Saverio Salzo

In existing distributed stochastic optimization studies, it is usually assumed that the gradient noise has a bounded variance. However, recent research shows that the heavy-tailed noise, which allows an unbounded variance, is closer to…

Optimization and Control · Mathematics 2025-05-15 Jun Hu , Chao Sun , Bo Chen , Jianzheng Wang , Zheming Wang

Score-based generative modeling, implemented through probability flow ODEs, has shown impressive results in numerous practical settings. However, most convergence guarantees rely on restrictive regularity assumptions on the target…

Machine Learning · Statistics 2025-10-21 Gitte Kremling , Francesco Iafrate , Mahsa Taheri , Johannes Lederer

Uncertainty estimation is a key issue when considering the application of deep neural network methods in science and engineering. In this work, we introduce a novel algorithm that quantifies epistemic uncertainty via Monte Carlo sampling…

Machine Learning · Statistics 2024-12-06 Sebastian Bieringer , Gregor Kasieczka , Maximilian F. Steffen , Mathias Trabs

In this paper, we analyse a proximal method based on the idea of forward-backward splitting for sampling from distributions with densities that are not necessarily smooth. In particular, we study the non-asymptotic properties of the…

Numerical Analysis · Mathematics 2022-01-25 Armin Eftekhari , Luis Vargas , Konstantinos Zygalakis

We introduce a novel and efficient algorithm called the stochastic approximate gradient descent (SAGD), as an alternative to the stochastic gradient descent for cases where unbiased stochastic gradients cannot be trivially obtained.…

Machine Learning · Computer Science 2020-02-14 Yixuan Qiu , Xiao Wang

Transfer Learning aims to optimally aggregate samples from a target distribution, with related samples from a so-called source distribution to improve target risk. Multiple procedures have been proposed over the last two decades to address…

Machine Learning · Statistics 2025-04-29 Steve Hanneke , Samory Kpotufe

An algorithm is proposed, analyzed, and tested for minimizing locally Lipschitz objective functions that may be nonconvex and/or nonsmooth. The algorithm, which is built upon the gradient-sampling methodology, is designed specifically for…

Optimization and Control · Mathematics 2026-04-02 Albert S. Berahas , Frank E. Curtis , Lara Zebiane