Seminar: Flexible and deep models for density estimation

SpeakerIain Murray
AffiliationEdinburgh University
DateFriday, 20 Mar 2015
Time13:00 - 14:00
LocationRoberts G06 (Sir Ambrose Fleming lecture theatre)
Event seriesMicrosoft Research CSML Seminar Series
Description

We bring the empirical success of deep neural network models in
regression and classification to high-dimensional density estimation.
Using the product rule, density estimation in D-dimensions can be
reduced to D regression tasks. We tie these tasks together to improve
computational and statistical efficiency, obtaining state-of-the-art
fits across a wide range of benchmark tasks. I'll give an example
Bayesian data analysis application from cosmology.

Speaker website

Work with Benigno Uria and Hugo Larochelle.

iCalendar csml_id_214.ics