↓Skip to main content

Samuel Kaski

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% 🎉)

2024

Analyzing GFlowNets: Stability, Expressiveness, and Assessment

·288 words
Tiago Da Silva Eliezer De Souza Da Silva Rodrigo Barreto Alves Luiz Max Carvalho Amauri H Souza Samuel Kaski Vikas Garg Diego Mesquita Publication Preprint Workshop SPIGM@ICML Deep Generative Models Theoretical ML Generative Flow Networks

How balance violations impact the learned distribution, motivating an weighted balance loss to improve training. For graph distributions, there are scenarios where balance is unattainable, and richer embeddings of children’s states is needed enhance expressiveness. To measure of distributional correctness in GFN we introduce a provable correct novel assessment metric.

2023

Human-in-the-Loop Causal Discovery under Latent Confounding using Ancestral GFlowNets

·288 words
Tiago Da Silva Eliezer De Souza Da Silva Adèle Ribeiro António Góis Dominik Heider Samuel Kaski Diego Mesquita Publication Preprint Generative Flow Networks Causal Structure Learning Causal ML

We introduce a causal discovery method that estimates uncertainty and refines results with expert feedback. Using generative flow networks, we sample belief-based ancestral graphs that captures latent-confounding, and iteratively reduce uncertainty through human input, with a human-in-the-loop approach.