Showing 2023Show all
2 papers · 1 filter
cs.LG2023
Balanced Training of Energy-Based Models with Adaptive Flow Sampling
Louis Grenioux, Éric Moulines, Marylou Gabrié
Energy-based models (EBMs) are versatile density estimation models that directly parameterize an unnormalized log density. Although very flexible, EBMs lack a specified normalizati…
stat.ML2023
On Sampling with Approximate Transport Maps
Louis Grenioux, Alain Durmus, Éric Moulines +1
Transport maps can ease the sampling of distributions with non-trivial geometries by transforming them into distributions that are easier to handle. The potential of this approach…