Edinburgh Research Explorer

Distilling Intractable Generative Models

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

Original languageEnglish
Title of host publicationProbabilistic Integration Workshop at the Neural Information Processing Systems Conference, 2015
Number of pages5
Publication statusAccepted/In press - 2 Aug 2015

Abstract

A generative model’s partition function is typically expressed as an intractable multi-dimensional integral, whose approximation presents a challenge to numerical and Monte Carlo integration. In this work, we propose a new estimation method for intractable partition functions, based on distilling an intractable generative model into a tractable approximation thereof, and using the latter for proposing Monte Carlo samples. We empirically demonstrate that our method -of-the-art estimates, even in combination with simple Monte Carlo methods.

Download statistics

No data available

ID: 26480716