Speaker:

Pierre Alquier, RIKEN Center for Advanced Intelligence Project (AIP), Tokyo, Japan

Talk abstract:

Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even under model mismatch and with 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 talk, we show that this is indeed the case for some variational inference (VI) algorithms. We propose new online, tempered VI algorithms and derive their generalization bounds. Our theoretical result relies on the convexity of the variational objective, but we argue that our result should hold more generally and present empirical evidence in support of this. Our work in this paper presents theoretical justifications in favour of online algorithms that rely on approximate Bayesian methods.

Bristol Data Science Seminars

The Jean Golding Institute has teamed up with the Heilbronn Institute for Mathematical Research. We will be showcasing the latest research in Data Science methodology with roots in Mathematics and Computer Science with important applied implications.

Read more about the Bristol Data Science Seminars.

Join our mailing list

To keep up to date with events like this, as well as funding, news, blogs and more, join our mailing list

***Please note the amended date, time and location for this seminar***