\dm_csml_event_details UCL ELLIS

Flexible and deep models for density estimation


Speaker

Iain Murray

Affiliation

Edinburgh University

Date

Friday, 20 March 2015

Time

13:00-14:00

Location

Zoom

Link

Roberts G06 (Sir Ambrose Fleming lecture theatre)

Event series

DeepMind/ELLIS CSML Seminar Series

Abstract

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.

Biography