Convergence Guarantees for Adaptive Bayesian Quadrature Methods

05/24/2019
by   Motonobu Kanagawa, et al.
0

Adaptive Bayesian quadrature (ABQ) is a powerful approach to numerical integration that empirically compares favorably with Monte Carlo integration on problems of medium dimensionality (where non-adaptive quadrature is not competitive). Its key ingredient is an acquisition function that changes as a function of previously collected values of the integrand. While this adaptivity appears to be empirically powerful, it complicates analysis. Consequently, there are no theoretical guarantees so far for this class of methods. In this work, for a broad class of adaptive Bayesian quadrature methods, we prove consistency, deriving non-tight but informative convergence rates. To do so we introduce a new concept we call weak adaptivity. In guaranteeing consistency of ABQ, weak adaptivity is notionally similar to the ideas of detailed balance and ergodicity in Markov Chain Monte Carlo methods, which allow sufficient conditions for consistency of MCMC. Likewise, our results identify a large and flexible class of adaptive Bayesian quadrature rules as consistent, within which practitioners can develop empirically efficient methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/26/2019

Convergence diagnostics for Markov chain Monte Carlo

Markov chain Monte Carlo (MCMC) is one of the most useful approaches to ...
research
08/18/2017

In Search of Lost (Mixing) Time: Adaptive Markov chain Monte Carlo schemes for Bayesian variable selection with very large p

The availability of data sets with large numbers of variables is rapidly...
research
10/25/2021

Adaptation of the Independent Metropolis-Hastings Sampler with Normalizing Flow Proposals

Markov Chain Monte Carlo (MCMC) methods are a powerful tool for computat...
research
01/28/2018

Air Markov Chain Monte Carlo

We introduce a class of Adapted Increasingly Rarely Markov Chain Monte C...
research
05/23/2019

Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting

Performing exact Bayesian inference for complex models is intractable. M...
research
12/04/2018

Batch Selection for Parallelisation of Bayesian Quadrature

Integration over non-negative integrands is a central problem in machine...
research
06/08/2015

Frank-Wolfe Bayesian Quadrature: Probabilistic Integration with Theoretical Guarantees

There is renewed interest in formulating integration as an inference pro...

Please sign up or login with your details

Forgot password? Click here to reset