English
Related papers

Related papers: Aggregated Gradient Langevin Dynamics

200 papers

We study the mixing properties of an important optimization algorithm of machine learning: the stochastic gradient Langevin dynamics (SGLD) with a fixed step size. The data stream is not assumed to be independent hence the SGLD is not a…

Probability · Mathematics 2023-08-01 Attila Lovas , Miklós Rásonyi

The Gaussian process latent variable model (GPLVM) is a popular probabilistic method used for nonlinear dimension reduction, matrix factorization, and state-space modeling. Inference for GPLVMs is computationally tractable only when the…

Machine Learning · Statistics 2023-06-16 Michael Minyi Zhang , Gregory W. Gundersen , Barbara E. Engelhardt

The generalized linear mixed model (GLMM) is widely used for analyzing correlated data, particularly in large-scale biomedical and social science applications. Scalable Bayesian inference for GLMMs is challenging because the marginal…

Computation · Statistics 2026-01-07 Samuel I. Berchuck , Youngsoo Baek , Felipe A. Medeiros , Andrea Agazzi

Bayesian neural networks (BNNs) allow us to reason about uncertainty in a principled way. Stochastic Gradient Langevin Dynamics (SGLD) enables efficient BNN learning by drawing samples from the BNN posterior using mini-batches. However,…

Machine Learning · Computer Science 2018-06-28 Kuan-Chieh Wang , Paul Vicol , James Lucas , Li Gu , Roger Grosse , Richard Zemel

The linear Markov Decision Process (MDP) framework offers a principled foundation for reinforcement learning (RL) with strong theoretical guarantees and sample efficiency. However, its restrictive assumption-that both transition dynamics…

Machine Learning · Statistics 2025-06-03 Sinian Zhang , Kaicheng Zhang , Ziping Xu , Tianxi Cai , Doudou Zhou

It is known that gradient-based MCMC samplers for continuous spaces, such as Langevin Monte Carlo (LMC), can be derived as particle versions of a gradient flow that minimizes KL divergence on a Wasserstein manifold. The superior efficiency…

Machine Learning · Computer Science 2023-02-24 Haoran Sun , Hanjun Dai , Bo Dai , Haomin Zhou , Dale Schuurmans

This paper presents AGGLIO (Accelerated Graduated Generalized LInear-model Optimization), a stage-wise, graduated optimization technique that offers global convergence guarantees for non-convex optimization problems whose objectives offer…

Optimization and Control · Mathematics 2021-11-09 Debojyoti Dey , Bhaskar Mukhoty , Purushottam Kar

Adaptive and interacting Markov Chains Monte Carlo (MCMC) algorithms are a novel class of non-Markovian algorithms aimed at improving the simulation efficiency for complicated target distributions. In this paper, we study a general…

Statistics Theory · Mathematics 2011-07-15 Gersende Fort , Eric Moulines , Pierre Priouret , Pierre Vandekerkhove

The Hamiltonian Monte Carlo (HMC) sampling algorithm exploits Hamiltonian dynamics to construct efficient Markov Chain Monte Carlo (MCMC), which has become increasingly popular in machine learning and statistics. Since HMC uses the gradient…

Machine Learning · Computer Science 2019-06-04 Minghao Gu , Shiliang Sun

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

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

To stabilize the training of Large Language Models (LLMs), gradient clipping is a nearly ubiquitous heuristic used to alleviate exploding gradients. However, traditional global norm clipping erroneously presupposes gradient homogeneity…

Machine Learning · Computer Science 2026-01-21 Zhiyuan Li , Yuan Wu , Yi Chang

We present a framework for adaptive-stepsize MCMC sampling based on time-rescaled Langevin dynamics, in which the stepsize variation is dynamically driven by an additional degree of freedom. Our approach augments the phase space by an…

Computation · Statistics 2025-05-27 Benedict Leimkuhler , René Lohmann , Peter Whalley

We study Langevin-type algorithms for sampling from Gibbs distributions such that the potentials are dissipative and their weak gradients have finite moduli of continuity not necessarily convergent to zero. Our main result is a…

Statistics Theory · Mathematics 2024-03-01 Shogo Nakakita

The wide applications of Generative adversarial networks benefit from the successful training methods, guaranteeing that an object function converges to the local minima. Nevertheless, designing an efficient and competitive training method…

Machine Learning · Computer Science 2021-11-11 Huiqing Qi , Fang Li , Shengli Tan , Xiangyun Zhang

Bayesian methods of sampling from a posterior distribution are becoming increasingly popular due to their ability to precisely display the uncertainty of a model fit. Classical methods based on iterative random sampling and posterior…

Machine Learning · Statistics 2022-11-04 Jacopo Guidolin , Vyacheslav Kungurtsev , Ondřej Kuželka

Sampling from log-concave distributions is a well researched problem that has many applications in statistics and machine learning. We study the distributions of the form $p^{*}\propto\exp(-f(x))$, where…

Machine Learning · Computer Science 2019-09-13 Ruoqi Shen , Yin Tat Lee

We consider adaptive increasingly rare Markov chain Monte Carlo (MCMC) algorithms, which are adaptive MCMC methods, where the adaptation concerning the "past'' happens less and less frequently over time. Under a contraction assumption with…

Numerical Analysis · Mathematics 2026-02-24 Julian Hofstadler , Krzysztof Latuszynski , Gareth O. Roberts , Daniel Rudolf

An intriguing new class of piecewise deterministic Markov processes (PDMPs) has recently been proposed as an alternative to Markov chain Monte Carlo (MCMC). In order to facilitate the application to a larger class of problems, we propose a…

Computation · Statistics 2022-05-24 Matthias Sachs , Deborshee Sen , Jianfeng Lu , David Dunson

In this paper, we propose a unified convergence analysis for a class of generic shuffling-type gradient methods for solving finite-sum optimization problems. Our analysis works with any sampling without replacement strategy and covers many…

Optimization and Control · Mathematics 2021-09-21 Lam M. Nguyen , Quoc Tran-Dinh , Dzung T. Phan , Phuong Ha Nguyen , Marten van Dijk