activity
20172022
most citedInformed proposals for local MCMC in discrete spaces

1 citations · 1 across the 2 of their papers we have counts for

collaborators

8 papers

stat.CO2022

Optimal design of the Barker proposal and other locally-balanced Metropolis-Hastings algorithms

Jure Vogrinc, Samuel Livingstone, Giacomo Zanella

We study the class of first-order locally-balanced Metropolis--Hastings algorithms introduced in Livingstone & Zanella (2021). To choose a specific algorithm within the class the u…

stat.CO2020

A fresh take on 'Barker dynamics' for MCMC

Max Hird, Samuel Livingstone, Giacomo Zanella

We study a recently introduced gradient-based Markov chain Monte Carlo method based on 'Barker dynamics'. We provide a full derivation of the method from first principles, placing…

stat.ME2020

Random Partition Models for Microclustering Tasks

Brenda Betancourt, Giacomo Zanella, Rebecca C. Steorts

Traditional Bayesian random partition models assume that the size of each cluster grows linearly with the number of data points. While this is appealing for some applications, this…

stat.CO2019

The Barker proposal: combining robustness and efficiency in gradient-based MCMC

Samuel Livingstone, Giacomo Zanella

There is a tension between robustness and efficiency when designing Markov chain Monte Carlo (MCMC) sampling algorithms. Here we focus on robustness with respect to tuning paramete…

stat.CO2018

Scalable Importance Tempering and Bayesian Variable Selection

Giacomo Zanella, Gareth Roberts

We propose a Monte Carlo algorithm to sample from high dimensional probability distributions that combines Markov chain Monte Carlo and importance sampling. We provide a careful th…

stat.CO2018

Scalable inference for crossed random effects models

Omiros Papaspiliopoulos, Gareth O. Roberts, Giacomo Zanella

We analyze the complexity of Gibbs samplers for inference in crossed random effect models used in modern analysis of variance. We demonstrate that for certain designs the plain van…