Jean Barbier

Permanent Scientific Staff
Research Scientist
Me
+39 040 2240 4146
jbarbier@ictp.it
+39 040 2240 4146
jbarbier@ictp.it
SISSA-216
https://jeanbarbier.github.io/
0000-0002-2652-6727

Jean Barbier

I am a mathematical physicist working on high-dimensional inference and the theory of neural networks, using statistical physics of disordered systems, random matrix and information theory.

My group is funded by the ERC Starting Grant CHORAL (Computational Hardness Of RepresentAtion Learning). We study the fundamental and algorithmic limits of high-dimensional inference and of learning in neural networks, using the statistical physics of disordered systems, random matrix theory and information theory. We look for sharp answers: how much data is needed, which phase transitions occur, and how close efficient algorithms come to optimal performance. More recently we also study how the training dynamics of neural networks discovers features, where neural scaling laws come from, and questions of interpretability: how to read what a trained network has learned.

Publications

Journal article
2021
Adaptive path interpolation method for sparse systems: Application to a censored block model
IEEE Transactions on Information Theory (2021)
Barbier, J. | Chan, C.L. | Macris, N.
Journal article
2020
Blind calibration for compressed sensing: State evolution and an online algorithm
Journal of Physics A: Mathematical and Theoretical (2020)
Gabrié, M. | Barbier, J. | Krzakala, F. | Zdeborová, L.
Journal article
2020
Mutual information for low-rank even-order symmetric tensor estimation
Information and Inference: A Journal of the IMA (2020)
Jean Barbier
Journal article
2020
Concentration of Multi-overlaps for Random Dilute Ferromagnetic Spin Models
Journal of Statistical Physics (2020)
Jean Barbier
Journal article
2020
Mutual Information and Optimality of Approximate Message-Passing in Random Linear Estimation
IEEE Transactions on Information Theory (2020)
Jean Barbier
Journal article
2020
Overlap matrix concentration in optimal Bayesian inference
Information and Inference: A Journal of the IMA (2020)
Jean Barbier
Journal article
2019
Optimal errors and phase transitions in high-dimensional generalized linear models
Proceedings of the National Academy of Sciences (2019)
Jean Barbier
Journal article
2019
Entropy and mutual information in models of deep neural networks
Journal of Statistical Mechanics: Theory and Experiment (2019)
Jean Barbier
Journal article
2019
The committee machine: computational to statistical gaps in learning a two-layers neural network
Journal of Statistical Mechanics: Theory and Experiment (2019)
Jean Barbier
Journal article
2019
The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference
Probability Theory and Related Fields (2019)
Jean Barbier
Journal article
2019
The adaptive interpolation method for proving replica formulas. Applications to the Curie–Weiss and Wigner spike models
Journal of Physics A: Mathematical and Theoretical (2019)
Jean Barbier
Journal article
2017
Approximate Message-Passing Decoder and Capacity Achieving Sparse Superposition Codes
IEEE Transactions on Information Theory (2017)
Barbier, J. | Krzakala, F.
Journal article
2015
Approximate message-passing with spatially coupled structured operators, with applications to compressed sensing and sparse superposition codes
Journal of Statistical Mechanics: Theory and Experiment (2015)
Barbier, J. | Schülke, C. | Krzakala, F.

Sorry no results