Stochastic Stein Discrepancies

07/06/2020
by   Jackson Gorham, et al.
0

Stein discrepancies (SDs) monitor convergence and non-convergence in approximate inference when exact integration and sampling are intractable. However, the computation of a Stein discrepancy can be prohibitive if the Stein operator - often a sum over likelihood terms or potentials - is expensive to evaluate. To address this deficiency, we show that stochastic Stein discrepancies (SSDs) based on subsampled approximations of the Stein operator inherit the convergence control properties of standard SDs with probability 1. In our experiments with biased Markov chain Monte Carlo (MCMC) hyperparameter tuning, approximate MCMC sampler selection, and stochastic Stein variational gradient descent, SSDs deliver comparable inferences to standard SDs with orders of magnitude fewer likelihood evaluations.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/10/2018

Bayesian variational inference for exponential random graph models

Bayesian inference for exponential random graphs (ERGMs) is a doubly int...
06/03/2015

Parallel Stochastic Gradient Markov Chain Monte Carlo for Matrix Factorisation Models

For large matrix factorisation problems, we develop a distributed Markov...
06/26/2020

On the convergence of the Metropolis algorithm with fixed-order updates for multivariate binary probability distributions

The Metropolis algorithm is arguably the most fundamental Markov chain M...
11/29/2017

Particle Optimization in Stochastic Gradient MCMC

Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has been increasi...
07/04/2015

Inference for determinantal point processes without spectral knowledge

Determinantal point processes (DPPs) are point process models that natur...
10/24/2020

Lightning-Fast Gravitational Wave Parameter Inference through Neural Amortization

Gravitational waves from compact binaries measured by the LIGO and Virgo...
02/13/2020

Stochastic Approximate Gradient Descent via the Langevin Algorithm

We introduce a novel and efficient algorithm called the stochastic appro...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.