↓Skip to main content

Theoretical Machine Learning

2025

When do GFlowNets Learn the Right Distribution?

·274 words
Tiago Da Silva Rodrigo Barreto Alves Eliezer De Souza Da Silva Amauri H Souza Vikas Garg Samuel Kaski Diego Mesquita Publication Spotlight Paper Conference ICLR Generative Flow Networks Generative Models Theoretical Machine Learning

Analysis of the limitations and stability of GFlowNets under balance violations, showing how these affect accuracy. We introduce a novel metric for assessing correctness, improving evaluation beyond existing protocols.

ICLR 2025 (Spotlight, ~top 5% 🎉)