English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
  A note on the evaluation of generative models

Theis, L., van den Oord, A., & Bethge, M. (2016). A note on the evaluation of generative models. In International Conference on Learning Representations (ICLR 2016) (pp. 1-10).

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0000-7A96-E Version Permalink: http://hdl.handle.net/21.11116/0000-0000-7A97-D
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
Link (Any fulltext)
Description:
-

Creators

show
hide
 Creators:
Theis, L1, 2, Author              
van den Oord, A, Author
Bethge, M1, 2, Author              
Affiliations:
1Research Group Computational Vision and Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497805              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Probabilistic generative models can be used for compression, denoising, inpainting, texture synthesis, semi-supervised learning, unsupervised feature learning, and other tasks. Given this wide range of applications, it is not surprising that a lot of heterogeneity exists in the way these models are formulated, trained, and evaluated. As a consequence, direct comparison between models is often difficult. This article reviews mostly known but often underappreciated properties relating to the evaluation and interpretation of generative models with a focus on image models. In particular, we show that three of the currently most commonly used criteria---average log-likelihood, Parzen window estimates, and visual fidelity of samples---are largely independent of each other when the data is high-dimensional. Good performance with respect to one criterion therefore need not imply good performance with respect to the other criteria. Our results show that extrapolation from one criterion to another is not warranted and generative models need to be evaluated directly with respect to the application(s) they were intended for. In addition, we provide examples demonstrating that Parzen window estimates should generally be avoided.

Details

show
hide
Language(s):
 Dates: 2016-05
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: TheisvB2016
 Degree: -

Event

show
hide
Title: International Conference on Learning Representations (ICLR 2016)
Place of Event: San Juan, Puerto Rico
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: International Conference on Learning Representations (ICLR 2016)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1 - 10 Identifier: -