arXiv Machine Learning June 2, 2026 By Yu Wang, Jie Ding, Jonathan H. Huggins

Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo

Read the original on arXiv Machine Learning →

arXiv:2606. 00293v1 Announce Type: new Abstract: Tuning algorithms such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty quantification remains challenging, particularly in the practically relevant settings when the batch size is large or the model is misspecified.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 2

Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo

arXiv:2606. 00309v1 Announce Type: new Abstract: Stochastic gradient Langevin dynamics combined with Gibbs updates (SGLD--Gibbs) provides a highly scalable approach to approximate Bayesian inference in latent variable models.

By Xiaoyu Wang, Jonathan H. Huggins

diffusion

arXiv Machine Learning

Aug 3

Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance

arXiv:2605. 26000v2 Announce Type: replace-cross Abstract: Stochastic gradient descent (SGD) is foundational to large-scale statistical learning and stochastic optimization.

By Jose Blanchet, Peter Glynn, Wenhao Yang

arXiv Machine Learning

Jun 30

Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms

arXiv:2606. 28808v1 Announce Type: cross Abstract: We study the leading-order fluctuation of stochastic gradient Euler-Maruyama estimators for generalized non-reversible Langevin dynamics.

By Bingye Ni, Xiaoyu Wang, Yingli Wang, Lingjiong Zhu

diffusion

arXiv Machine Learning

Jul 9

Gradient-free Riemannian Langevin Sampler

arXiv:2607. 07519v1 Announce Type: new Abstract: We address the problem of efficiently sampling multimodal probability distributions, where standard Markov Chain Monte Carlo methods often suffer from poor mixing and mode trapping.

By Ricardo Baptista, Olivier Zahm

multimodal benchmarks

Hugging Face Trending Papers

Jul 8

Gradient-free Riemannian Langevin Sampler

We address the problem of efficiently sampling multimodal probability distributions, where standard Markov Chain Monte Carlo methods often suffer from poor mixing and mode trapping. To mitigate these issues, we propose Gradient-free Riemannian Langevin Sampler (GRiLS), a novel proposal that improves exploration without requiring gradient evaluations of the target density.

multimodal benchmarks

arXiv AI

Jun 2

Efficient Weighted Sampling via Score-based Generative Models

arXiv:2502. 04646v2 Announce Type: replace-cross Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, biased sampling, data augmentation, and more.

By Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana

diffusion benchmarks

Related stories

Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo

Statistical Inference for Stochastic Gradient Descent: Beyond Finite Variance

Variance Reduction for Stochastic Gradient Generalized Non-reversible Langevin Monte Carlo Algorithms

Gradient-free Riemannian Langevin Sampler

Gradient-free Riemannian Langevin Sampler

Efficient Weighted Sampling via Score-based Generative Models