150 citations · 347 across the 14 of their papers we have counts for
14 papers
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…
PDMP characterisation of event-chain Monte Carlo algorithms for particle systems
Athina Monemvassitis, Arnaud Guillin, Manon Michel
Monte Carlo simulations of systems of particles such as hard spheres or soft spheres with singular kernels can display around a phase transition prohibitively long convergence time…
Law of large numbers and central limit theorem for wide two-layer neural networks: the mini-batch and noisy case
Arnaud Descours, Arnaud Guillin, Manon Michel +1
In this work, we consider a wide two-layer neural network and study the behavior of its empirical weights under a dynamics set by a stochastic gradient descent along the quadratic…
Loop-Cluster Coupling and Algorithm for Classical Statistical Models
Lei Zhang, Manon Michel, Eren M. Elçi +1
Potts spin systems play a fundamental role in statistical mechanics and quantum field theory, and can be studied within the spin, the Fortuin-Kasteleyn (FK) bond or the -flow (l…
Clock Monte Carlo methods
Manon Michel, Xiaojun Tan, Youjin Deng
We propose the clock Monte Carlo technique for sampling each successive chain step in constant time. It is built on a recently proposed factorized transition filter and its core fe…
Forward Event-Chain Monte Carlo: Fast sampling by randomness control in irreversible Markov chains
Manon Michel, Alain Durmus, Stéphane Sénécal
Irreversible and rejection-free Monte Carlo methods, recently developed in Physics under the name Event-Chain and known in Statistics as Piecewise Deterministic Monte Carlo (PDMC),…
Event-chain Monte Carlo algorithms for three- and many-particle interactions
Julian Harland, Manon Michel, Tobias A. Kampmann +1
We generalize the rejection-free event-chain Monte Carlo algorithm from many particle systems with pairwise interactions to systems with arbitrary three- or many-particle interacti…
Event-chain algorithm for the Heisenberg model: Evidence for dynamic scaling
Yoshihiko Nishikawa, Manon Michel, Werner Krauth +1
We apply the event-chain Monte Carlo algorithm to the three-dimensional ferromagnetic Heisenberg model. The algorithm is rejection-free and also realizes an irreversible Markov cha…
Event-chain Monte Carlo for classical continuous spin models
Manon Michel, Johannes Mayer, Werner Krauth
We apply the event-chain Monte Carlo algorithm to classical continuum spin models on a lattice and clarify the condition for its validity. In the two-dimensional XY model, it outpe…
Generalized event-chain Monte Carlo: Constructing rejection-free global-balance algorithms from infinitesimal steps
Manon Michel, Sebastian C. Kapfer, Werner Krauth
In this article, we present an event-driven algorithm that generalizes the recent hard-sphere event-chain Monte Carlo method without introducing discretizations in time or in space…
Mass distributions of stars and cores in young groups and clusters
Manon Michel, Helen Kirk, Philip C. Myers
We investigate the relation of the stellar initial mass function (IMF) and the dense core mass function (CMF), using stellar masses and positions in 14 well-studied young groups. I…