A theory of continuous generative flow networks

Salem Lahlou*, Tristan Deleu, Pablo Lemos, Dinghuai Zhang, Alexandra Volokhova, Alex Hernández-García, Léna Néhale Ezzine, Yoshua Bengio, Nikolay Malkin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.
Original languageEnglish
Title of host publicationProceedings of the 40th International Conference on Machine Learning
EditorsAndreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, Jonathan Scarlett
PublisherPMLR
Pages18269-18300
Number of pages32
Volume202
Publication statusPublished - 29 Jul 2023
EventThe Fortieth International Conference on Machine Learning - Honolulu, United States
Duration: 23 Jul 202329 Jul 2023
Conference number: 40
https://icml.cc/

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
ISSN (Print)2640-3498

Conference

ConferenceThe Fortieth International Conference on Machine Learning
Abbreviated titleICML 2023
Country/TerritoryUnited States
CityHonolulu
Period23/07/2329/07/23
Internet address

Fingerprint

Dive into the research topics of 'A theory of continuous generative flow networks'. Together they form a unique fingerprint.

Cite this