collaborators

6 papers

stat.CO2026

Large-scale empirical tuning and comparison of default optimizers for variational inference

Trevor Campbell, Jonathan H. Huggins, Kyurae Kim +1

Black-box variational inference (BBVI) is a methodology for posterior approximation that relies on stochastic optimization. In practice, the stochastic optimizers underpinning BBVI…

cs.LG2026

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

Xiaoyu Wang, Jonathan H. Huggins

Stochastic gradient Langevin dynamics combined with Gibbs updates (SGLD--Gibbs) provides a highly scalable approach to approximate Bayesian inference in latent variable models. How…

cs.LG2026

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

Yu Wang, Jie Ding, Jonathan H. Huggins

Tuning algorithms such as stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD) for approximate sampling and uncertainty quantification remains challen…

stat.ME2026

Surrogate-Based Bayesian Inference: Uncertainty Quantification and Active Learning

Andrew Gerard Roberts, Michael C. Dietze, Jonathan H. Huggins

Surrogate models - also called emulators - are widely used to facilitate Bayesian inference in settings where computational costs preclude the use of standard posterior inference a…

stat.CO2025

Tuning-Free Coreset Markov Chain Monte Carlo via Hot DoG

Naitong Chen, Jonathan H. Huggins, Trevor Campbell

A Bayesian coreset is a small, weighted subset of a data set that replaces the full data during inference to reduce computational cost. The state-of-the-art coreset construction al…

stat.ML2025

Quantitative Error Bounds for Scaling Limits of Stochastic Iterative Algorithms

Xiaoyu Wang, Mikolaj J. Kasprzak, Jeffrey Negrea +2

Stochastic iterative algorithms, including stochastic gradient descent (SGD) and stochastic gradient Langevin dynamics (SGLD), are widely utilized for optimization and sampling in…