Comparison of Markov chains via weak Poincaré inequalities with application to pseudo-marginal MCMC

no code implementations • 10 Dec 2021 • Christophe Andrieu, Anthony Lee, Sam Power, Andi Q. Wang

We investigate the use of a certain class of functional inequalities known as weak Poincar\'e inequalities to bound convergence of Markov chains to equilibrium.

Accelerating sequential Monte Carlo with surrogate likelihoods

1 code implementation • 8 Sep 2020 • Joshua J Bon, Anthony Lee, Christopher Drovandi

Delayed-acceptance is a technique for reducing computational effort for Bayesian models with expensive likelihoods.

Computation Methodology

Coupled conditional backward sampling particle filter

1 code implementation • 15 Jun 2018 • Anthony Lee, Sumeetpal S. Singh, Matti Vihola

This complements the earlier findings in the literature for conditional particle filters, which assume the number of particles to grow (super)linearly in terms of the time horizon.

Computation Probability Primary 65C05, secondary 60J05, 65C35, 65C40

Unbiased approximations of products of expectations

1 code implementation • 4 Sep 2017 • Anthony Lee, Simone Tiberi, Giacomo Zanella

This is wasteful and typically requires the number of particles to grow quadratically with the number of expectations.

Computation

Anytime Monte Carlo

no code implementations • 10 Dec 2016 • Lawrence M. Murray, Sumeetpal Singh, Anthony Lee

Monte Carlo algorithms simulate some prescribed number of samples, taking some random real time to complete the computations necessary.