Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  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

Basisdaten

einblenden: ausblenden:
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:
ausblenden:
externe Referenz:
Link (beliebiger Volltext)
Beschreibung:
-
OA-Status:

Urheber

einblenden:
ausblenden:
 Urheber:
Theis, L1, 2, Autor           
van den Oord, A, Autor
Bethge, M1, 2, Autor           
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              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: 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

einblenden:
ausblenden:
Sprache(n):
 Datum: 2016-05
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: TheisvB2016
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: International Conference on Learning Representations (ICLR 2016)
Veranstaltungsort: San Juan, Puerto Rico
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: International Conference on Learning Representations (ICLR 2016)
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1 - 10 Identifikator: -