English

A Generalization Bound for Online Variational Inference

Machine Learning 2020-08-03 v2 Machine Learning Statistics Theory Computation Statistics Theory

Abstract

Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even with model mismatch and adversaries. Unfortunately, exact Bayesian inference is rarely feasible in practice and approximation methods are usually employed, but do such methods preserve the generalization properties of Bayesian inference ? In this paper, we show that this is indeed the case for some variational inference (VI) algorithms. We consider a few existing online, tempered VI algorithms, as well as a new algorithm, and derive their generalization bounds. Our theoretical result relies on the convexity of the variational objective, but we argue that the result should hold more generally and present empirical evidence in support of this. Our work in this paper presents theoretical justifications in favor of online algorithms relying on approximate Bayesian methods.

Keywords

Cite

@article{arxiv.1904.03920,
  title  = {A Generalization Bound for Online Variational Inference},
  author = {Badr-Eddine Chérief-Abdellatif and Pierre Alquier and Mohammad Emtiyaz Khan},
  journal= {arXiv preprint arXiv:1904.03920},
  year   = {2020}
}

Comments

Published in the proceedings of ACML 2019

R2 v1 2026-06-23T08:32:36.240Z