Interpolating between sampling and variational inference with infinite stochastic mixtures

arXiv2110.09618MaRDI QIDQ6380705FDOQ6380705

Ari Benjamin, Ralf M. Haefner, Richard D. Lange, Xaq Pitkow

Publication date: 18 October 2021

Abstract: Sampling and Variational Inference (VI) are two large families of methods for approximate inference that have complementary strengths. Sampling methods excel at approximating arbitrary probability distributions, but can be inefficient. VI methods are efficient, but may misrepresent the true distribution. Here, we develop a general framework where approximations are stochastic mixtures of simple component distributions. Both sampling and VI can be seen as special cases: in sampling, each mixture component is a delta-function and is chosen stochastically, while in standard VI a single component is chosen to minimize divergence. We derive a practical method that interpolates between sampling and VI by solving an optimization problem over a mixing distribution. Intermediate inference methods then arise by varying a single parameter. Our method provably improves on sampling (reducing variance) and on VI (reducing bias+variance despite increasing variance). We demonstrate our method's bias/variance trade-off in practice on reference problems, and we compare outcomes to commonly used sampling and VI methods. This work takes a step towards a highly flexible yet simple family of inference methods that combines the complementary strengths of sampling and VI.

Has companion code repository: https://github.com/wrongu/sampling-variational-demos

This page was built for publication: Interpolating between sampling and variational inference with infinite stochastic mixtures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6380705)