Files in this item



application/pdfFANG-THESIS-2020.pdf (46MB)Restricted to U of Illinois
(no description provided)PDF


Title:Co-generation with GANs using AIS based HMC
Author(s):Fang, Tiantian
Advisor(s):Schwing, Alexander
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Co-Generation, generative model, annealed importance sampling
Abstract:Inferring the most likely configuration for a subset of variables of a joint distribution given the remaining ones – which we refer to as co-generation – is an important challenge that is computationally demanding for all but the simplest settings. This task has received a considerable amount of attention, particularly for classical ways of modeling distributions like structured prediction. In contrast, almost nothing is known about this task when considering recently proposed techniques for modeling high-dimensional distributions, particularly generative adversarial nets (GANs). Therefore, in this paper, we study the occurring challenges for co-generation with GANs. To address those challenges we develop an annealed importance sampling based Hamiltonian Monte Carlo co-generation algorithm. The presented approach significantly outperforms classical gradient based methods on a synthetic and on the CelebA and LSUN datasets.
Issue Date:2020-05-14
Rights Information:Copyright 2020 Tiantian Fang
Date Available in IDEALS:2020-08-26
Date Deposited:2020-05

This item appears in the following Collection(s)

Item Statistics