Overview Statistic: PDF-Downloads (blue) and Frontdoor-Views (gray)

Fast and unified path gradient estimators for normalizing flows

  • Recent work shows that path gradient estimators for normalizing flows have lower variance compared to standard estimators for variational inference, resulting in improved training. However, they are often prohibitively more expensive from a computational point of view and cannot be applied to maximum likelihood train- ing in a scalable manner, which severely hinders their widespread adoption. In this work, we overcome these crucial limitations. Specifically, we propose a fast path gradient estimator which improves computational efficiency significantly and works for all normalizing flow architectures of practical relevance. We then show that this estimator can also be applied to maximum likelihood training for which it has a regularizing effect as it can take the form of a given target energy func- tion into account. We empirically establish its superior performance and reduced variance for several natural sciences applications.

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics - number of accesses to the document
Metadaten
Author:Lorenz Vaitl, Ludwig Winkler, Lorenz Richter, Pan Kessel
Document Type:In Proceedings
Parent Title (English):International Conference on Learning Representations 2024
Year of first publication:2024
ArXiv Id:http://arxiv.org/abs/2403.15881
URL:https://openreview.net/pdf?id=zlkXLb3wpF
Accept ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.