The reviewed record of science sign in
Pith

arxiv: 2210.00580 · v3 · pith:KULRDHAN · submitted 2022-10-02 · cs.LG · stat.ML

GFlowNets and variational inference

Reviewed by Pithpith:KULRDHANopen to challenge →

classification cs.LG stat.ML
keywords gflownetsdistributionsalgorithmscasesdifferencesfamiliesinferencelearning
0
0 comments X
read the original abstract

This paper builds bridges between two families of probabilistic algorithms: (hierarchical) variational inference (VI), which is typically used to model distributions over continuous spaces, and generative flow networks (GFlowNets), which have been used for distributions over discrete structures such as graphs. We demonstrate that, in certain cases, VI algorithms are equivalent to special cases of GFlowNets in the sense of equality of expected gradients of their learning objectives. We then point out the differences between the two families and show how these differences emerge experimentally. Notably, GFlowNets, which borrow ideas from reinforcement learning, are more amenable than VI to off-policy training without the cost of high gradient variance induced by importance sampling. We argue that this property of GFlowNets can provide advantages for capturing diversity in multimodal target distributions.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Stable GFlowNets with Probabilistic Guarantees

    cs.LG 2026-05 unverdicted novelty 7.0

    Derives loss-to-TV bounds providing probabilistic guarantees for GFlowNets and introduces Stable GFlowNets algorithm for improved training stability and distributional fidelity.