Seminar: Wild approximate inference: why and how

SpeakerYingzhen Li
AffiliationUniversity of Cambridge
DateFriday, 01 Dec 2017
Time13:00 - 14:00
LocationRoberts Building G08 Sir David Davies LT
Event seriesDeepMind CSML Seminar Series

This talk describes very recent efforts on developing approximate inference algorithms that enables approximations of arbitrary form. I will start by revisiting fundamental tractability issues of Bayesian computation and argue that density evaluation of the approximate posterior is mostly unnecessary. Then I will present 4 different categories of wild approximate inference methods that has been explored recently, with the focus on two of them developed by myself and colleagues. I will briefly cover: 1. the amortised MCMC algorithm that improves the approximate posterior by following the particle update of a valid MCMC sampler; and 2. a gradient estimation method that allow variational inference to be applied to those approximate distributions without a tractable density.

iCalendar csml_id_328.ics