255 citations · 949 across the 71 of their papers we have counts for
82 papers
Diffusion annealed Langevin dynamics: a theoretical study
Patrick Cattiaux, Paula Cordero-Encinar, Arnaud Guillin
In this work we study the diffusion annealed Langevin dynamics, a score-based diffusion process recently introduced in the theory of generative models and which is an alternative t…
Some remarks on the effect of the Random Batch Method on phase transition
Arnaud Guillin, Pierre Le Bris, Pierre Monmarché
In this article, we focus on two toy models : the Curie-Weiss model and the system of particles in linear interactions in a double well confining potential. Both models, which…
Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
Arnaud Descours, Tom Huix, Arnaud Guillin +3
We provide a rigorous analysis of training by variational inference (VI) of Bayesian neural networks in the two-layer and infinite-width case. We consider a regression problem with…
Necessary and sufficient symmetries in Event-Chain Monte Carlo with generalized flows and Application to hard dimers
Tristan Guyon, Arnaud Guillin, Manon Michel
Event-Chain Monte Carlo (ECMC) methods generate continuous-time and non-reversible Markov processes which often display significant accelerations compared to reversible counterpart…
Jamming pair of general run-and-tumble particles: Exact results, symmetries and steady-state universality classes
Leo Hahn, Arnaud Guillin, Manon Michel
While run-and-tumble particles are a foundational model for self-propelled particles as bacteria or Janus particles, the analytical derivation of their steady state from the micros…
Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity
Vincent Souveton, Arnaud Guillin, Jens Jasche +2
Normalizing Flows (NF) are Generative models which transform a simple prior distribution into the desired target. They however require the design of an invertible mapping whose Jac…