Abstract Markov chain Monte Carlo (MCMC) algorithms are generally regarded as the gold
standard technique for Bayesian inference. They are theoretically well-understood and …

Over the last decade, neural networks have reached almost every field of science and
become a crucial part of various real world applications. Due to the increasing spread …

Vision transformer networks have shown superiority in many computer vision tasks. In this
paper, we take a step further by proposing a novel generative vision transformer with latent …

The Zig-Zag process and super-efficient sampling for Bayesian analysis of big data Page 1 The
Annals of Statistics 2019, Vol. 47, No. 3, 1288–1320 https://doi.org/10.1214/18-AOS1715 © …

We present a unified framework to analyze the global convergence of Langevin dynamics
based algorithms for nonconvex finite-sum optimization with $ n $ component functions. At …

We study the efficiency of Thompson sampling for contextual bandits. Existing Thompson
sampling-based algorithms need to construct a Laplace approximation (ie, a Gaussian …

We give algorithms for sampling several structured logconcave families to high accuracy.
We further develop a reduction framework, inspired by proximal point methods in convex …

It is well known that Markov chain Monte Carlo (MCMC) methods scale poorly with dataset
size. A popular class of methods for solving this issue is stochastic gradient MCMC …

Abstract Stochastic Gradient Langevin Dynamics (SGLD) has emerged as a key MCMC
algorithm for Bayesian learning from large scale datasets. While SGLD with decreasing step …

Recently, there have been conceptually new developments in Monte Carlo methods through
the introduction of new MCMC and sequential Monte Carlo (SMC) algorithms which are …