3 papers
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…
cs.LG2026
Denoising Score Matching with Random Features: Insights on Diffusion Models from Precise Learning Curves
Anand Jerry George, Rodrigo Veiga, Nicolas Macris
We theoretically investigate the phenomena of generalization and memorization in diffusion models. Empirical studies suggest that these phenomena are influenced by model complexity…
math.ST2025
Analysis of Diffusion Models for Manifold Data
Anand Jerry George, Rodrigo Veiga, Nicolas Macris
We analyze the time reversed dynamics of generative diffusion models. If the exact empirical score function is used in a regime of large dimension and exponentially large number of…