Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Information-Geometric Forward Policy Training in GFlowNets
Yordan Raykov, Rodrigo Veiga
Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects, requiring only an unnormalise…
stat.ML2024
Stochastic Gradient Flow Dynamics of Test Risk and its Exact Solution for Weak Features
Rodrigo Veiga, Anastasia Remizova, Nicolas Macris
We investigate the test risk of continuous-time stochastic gradient flow dynamics in learning theory. Using a path integral formulation we provide, in the regime of a small learnin…