> Detailanzeige

Fortuin, Vincent [Verfasser:in]; Li, Yingzhen [Verfasser:in]; Murphy, Kevin [Verfasser:in]; Mandt, Stephan [Verfasser:in]; Manduchi, Laura [Verfasser:in] ; Vincent Fortuin and Yingzhen Li and Kevin Murphy and Stephan Mandt and Laura Manduchi [Mitwirkende:r]

Challenges and Perspectives in Deep Generative Modeling (Dagstuhl Seminar 23072)

Literatur-
verwaltung

Zur
Merkliste

Lösche von
Merkliste

Per Whatsapp teilen

Schließen

Merkliste



Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
  • Medientyp: Sonstige Veröffentlichung; E-Artikel
  • Titel: Challenges and Perspectives in Deep Generative Modeling (Dagstuhl Seminar 23072)
  • Beteiligte: Fortuin, Vincent [Verfasser:in]; Li, Yingzhen [Verfasser:in]; Murphy, Kevin [Verfasser:in]; Mandt, Stephan [Verfasser:in]; Manduchi, Laura [Verfasser:in]
  • Erschienen: Schloss Dagstuhl – Leibniz-Zentrum für Informatik, 2023
  • Sprache: Englisch
  • DOI: https://doi.org/10.4230/DagRep.13.2.47
  • Schlagwörter: neural data compression ; representation learning ; out-of-distribution detection ; generative modeling ; deep generative models
  • Entstehung:
  • Anmerkungen: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
  • Beschreibung: Deep generative models, such as variational autoencoders, generative adversarial networks, normalizing flows, and diffusion probabilistic models, have attracted a lot of recent interest. However, we believe that several challenges hinder their more widespread adoption: (C1) the difficulty of objectively evaluating the generated data; (C2) challenges in designing scalable architectures for fast likelihood evaluation or sampling; and (C3) challenges related to finding reproducible, interpretable, and semantically meaningful latent representations. In this Dagstuhl Seminar, we have discussed these open problems in the context of real-world applications of deep generative models, including (A1) generative modeling of scientific data, (A2) neural data compression, and (A3) out-of-distribution detection. By discussing challenges C1-C3 in concrete contexts A1-A3, we have worked towards identifying commonly occurring problems and ways towards overcoming them. We thus foresee many future research collaborations to arise from this seminar and for the discussed ideas to form the foundation for fruitful avenues of future research. We proceed in this report by summarizing the main results of the seminar and then giving an overview of the different contributed talks and working group discussions.
  • Zugangsstatus: Freier Zugang