10 papers
Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models
Zuokai Wen, Louis Grenioux, Weinan E +1
Inference-time scaling adapts pretrained diffusion models to new sampling tasks without additional training. Existing methods rely primarily on Monte Carlo sampling with more parti…
Bridging Stochastic Flow Maps and Boltzmann Generators with Normalizing Flows
Louis Grenioux, RuiKang OuYang, Luhuan Wu
Generating independent, equilibrium samples of molecular systems at scale remains a central obstacle in computational statistical mechanics. Boltzmann Generators address this by pa…
Diffusion-based Annealed Boltzmann Generators : benefits, pitfalls and hopes
Louis Grenioux, Maxence Noble
Sampling configurations at thermodynamic equilibrium is a central challenge in statistical physics. Boltzmann Generators (BGs) tackle it by combining a generative model with a Mont…
A Diffusive Classification Loss for Learning Energy-based Generative Models
RuiKang OuYang, Louis Grenioux, José Miguel Hernández-Lobato
Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way is to use a series of time-dependent…
Boltzmann generators for amorphous particle systems
Louis Grenioux, Leonardo Galliano, Ludovic Berthier +2
Sampling configurations in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann generators address this problem by employing generative models t…
Improving the evaluation of samplers on multi-modal targets
Louis Grenioux, Maxence Noble, Marylou Gabrié
Addressing multi-modality constitutes one of the major challenges of sampling. In this reflection paper, we advocate for a more systematic evaluation of samplers towards two source…
Learned Reference-based Diffusion Sampling for multi-modal distributions
Maxence Noble, Louis Grenioux, Marylou Gabrié +1
Over the past few years, several approaches utilizing score-based diffusion have been proposed to sample from probability distributions, that is without having access to exact samp…
Stochastic Localization via Iterative Posterior Sampling
Louis Grenioux, Maxence Noble, Marylou Gabrié +1
Building upon score-based learning, new interest in stochastic localization techniques has recently emerged. In these models, one seeks to noise a sample from the data distribution…
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…
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…