University of Illinois Urbana-Champaign

Generative modeling using the sliced Wasserstein distance

Deshpande, Ishan

Content Files
DESHPANDE-THESIS-2018.pdf

Permalink

https://hdl.handle.net/2142/100951

Description

Title
Generative modeling using the sliced Wasserstein distance
Author(s)
Deshpande, Ishan
Issue Date
2018-04-11
Director of Research (if dissertation) or Advisor (if thesis)
Schwing, Alexander G.
Department of Study
Electrical & Computer Eng
Discipline
Electrical & Computer Engr
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Date of Ingest
2018-09-04T20:26:58Z
Keyword(s)
  • Machine Learning
  • Deep Learning
Abstract
Generative adversarial nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to be hard to optimize and often unstable. While the aforementioned problems are particularly true for early GAN formulations, there has been significant empirically motivated and theoretically founded progress to improve stability, for instance, by using the Wasserstein distance rather than the Jenson-Shannon divergence. Here, we consider an alternative formulation for generative modeling based on random projections which, in its simplest form, results in a single objective rather than a saddlepoint formulation. By augmenting this approach with a discriminator we improve its accuracy. We found our approach to be significantly more stable compared to even the improved Wasserstein GAN. Further, unlike the traditional GAN loss, the loss formulated in our method is a good measure of the actual distance between the distributions and, for the first time for GAN training, we are able to show estimates for the same.
Graduation Semester
2018-05
Type of Resource
text
Permalink
http://hdl.handle.net/2142/100951
Copyright and License Information
Copyright 2018 Ishan Deshpande

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois
Dissertations and Theses - Electrical and Computer Engineering
Dissertations and Theses in Electrical and Computer Engineering