Publications

You can find an up-to-date list of my publications on Hal or Google Scholar.

Preprints #

• Activity-driven clustering of jamming run-and-tumble particles: Exact three-body steady state by dynamical symmetry L. Hahn, A. Guillin, and M. Michel
  arXiv 2509.08945

• Convergence of non-reversible Markov processes via lifting and flow Poincaré inequality
  A. Eberle, A. Guillin, L. Hahn, F. Lörler, and M. Michel
  arXiv 2503.04238

• Central Limit Theorem for Bayesian Neural Networks trained with Variational Inference
  A. Descours, T. Huix, A. Guillin, M. Michel, É. Moulines, and B. Nectoux
  arXiv 2406.09048

Published #

• Long time analysis of a pair of on-lattice and continuous run-and-tumble particles with hard-core interactions
  A. Guillin, L. Hahn, and M. Michel
  Journal of Statistical Physics 192(9), 123 (2025)

• Bosonized 1D quantum systems through enhanced Event-Chain Monte Carlo
  O. Bouverot-Dupuis, A. Rosso, and M. Michel
  Physical Review B 112, 035148 (2025)

• Jamming pair of general run-and-tumble particles: Exact results, symmetries and steady-state universality classes
  L. Hahn, A. Guillin, and M. Michel
  Journal of Physics A: Mathematical and Theoretical (to appear, 2025)

• Fixed-kinetic Neural Hamiltonian Flows for enhanced interpretability and reduced complexity
  V. Souveton, A. Guillin, J. Jasche, G. Lavaux, and M. Michel
  Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS) (2024)

• Necessary and sufficient symmetries in Event-Chain Monte Carlo with generalized flows and application to hard dimers
  T. Guyon, A. Guillin, and M. Michel
  The Journal of Chemical Physics 160 (2), 024117 (2024) Editor’s Pick and 2023 JCP Emerging Investigators Special Collection

• Law of Large Numbers for Bayesian two-layer Neural Network trained with Variational Inference
  A. Descours, T. Huix, A. Guillin, M. Michel, É. Moulines, and B. Nectoux
  Proceedings of Thirty Sixth Conference on Learning Theory (COLT) (2023)

• Law of large numbers and central limit theorem for wide two-layer neural networks: the mini-batch and noisy case
  A. Descours, A. Guillin, M. Michel, and B. Nectoux
  Journal of Machine Learning Research 25 (208), 1-76 (2024)

• PDMP characterisation of event-chain Monte Carlo algorithms for particle systems
  A. Monemvassitis, A. Guillin, and M. Michel
  Journal of Statistical Physics 190, 66 (2023)

• Loop-Cluster Monte Carlo Algorithm for Classical Statistical Models
  L. Zhang, M. Michel, E. M. Elçi, and Y. Deng
  Physical Review Letters 125 (20), 200603 (2020)

• Forward Event-chain Monte Carlo: Fast Sampling by Randomness Control in Irreversible Markov Chains
  M. Michel, A. Durmus, and S. Sénécal
  JCGS, 29 (4), 689-702 (2020)

• Clock Monte Carlo methods
  M. Michel, X. Tan, and Y. Deng
  PRE, 99, 010105, Rapid Communication (2019)

• Event-chain Monte Carlo algorithms for three- and many-particle interactions
  J. Harland, M. Michel, T. A. Kampmann, and J. Kierfeld
  EPL, 117, 30001 (2017) editor’s choice

• Event-chain algorithm for the Heisenberg model: Evidence for z ~ 1 dynamic scaling
  Nishikawa Y., Michel M., Krauth W., Hukushima K.
  Physical Review E, 92, 063306 (2015)

• Event-chain Monte Carlo for classical continuous spin models
  Michel M., Mayer J., Krauth W.
  EPL, 112, 20003 (2015)

• Generalized event-chain Monte Carlo: Constructing rejection-free global-balance algorithms from infinitesimal steps
  Michel M., Kapfer S., Krauth W.
  Journal of Chemical Physics, 140, 054116 (2014)

• Mass distributions of stars and cores in young groups and clusters
  Michel M., Kirk H., Myers P.
  Astrophysical Journal, 735, 51 (2011)

Thesis #

• Analytical and computational developments around long-time behaviors of stochastic processes
  M. Michel, HDR thesis defended on June 28th, 2024 at UCA, Aubière, France

• Irreversible Markov chains by the factorized Metropolis filter: Algorithms and applications in particle systems and spin models
  M. Michel, PhD thesis defended on October 17th, 2016 at ENS, Paris, France