5 papers
Wasserstein Contraction of Coordinate Ascent Variational Inference
Rocco Caprio, Adrien Corenflos, Sam Power
We study the non-asymptotic contraction in Wasserstein distance of the sequential, parallel, and random-scan coordinate ascent variational inference algorithms. This is shown to ho…
Fast convergence of the Expectation Maximization algorithm under a logarithmic Sobolev inequality
Rocco Caprio, Adam M Johansen
We present a new framework for analysing the Expectation Maximization (EM) algorithm. Drawing on recent advances in the theory of gradient flows over Euclidean-Wasserstein spaces,…
Analysis of Multiple-try Metropolis via Poincaré inequalities
Rocco Caprio, Sam Power, Andi Q. Wang
We study the Multiple-try Metropolis algorithm using the framework of Poincaré inequalities. We describe the Multiple-try Metropolis as an auxiliary variable implementation of a r…
Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities
Rocco Caprio, Juan Kuntz, Samuel Power +1
We prove non-asymptotic error bounds for particle gradient descent (PGD, Kuntz et al., 2023), a recently introduced algorithm for maximum likelihood estimation of large latent vari…
A calculus for Markov chain Monte Carlo: studying approximations in algorithms
Rocco Caprio, Adam M. Johansen
Markov chain Monte Carlo (MCMC) algorithms are based on the construction of a Markov chain with transition probabilities leaving invariant a probability distribution of interest. I…