450 citations · 5.9k across the 79 of their papers we have counts for
80 papers
Modelling the influence of data structure on learning in neural networks: the hidden manifold model
Sebastian Goldt, Marc Mézard, Florent Krzakala +1
Understanding the reasons for the success of deep neural networks trained using stochastic gradient-based methods is a key open problem for the nascent theory of deep learning. The…
High-temperature Expansions and Message Passing Algorithms
Antoine Maillard, Laura Foini, Alejandro Lage Castellanos +3
Improved mean-field technics are a central theme of statistical physics methods applied to inference and learning. We revisit here some of these methods using high-temperature expa…
Multi-Layer Generalized Linear Estimation
Andre Manoel, Florent Krzakala, Marc Mézard +1
We consider the problem of reconstructing a signal from multi-layered (possibly) non-linear measurements. Using non-rigorous but standard methods from statistical physics we presen…
Mean-field message-passing equations in the Hopfield model and its generalizations
Marc Mezard
Motivated by recent progress in using restricted Boltzmann machines as preprocessing algorithms for deep neural network, we revisit the mean-field equations (belief-propagation and…
Dynamic message-passing equations for models with unidirectional dynamics
Andrey Y. Lokhov, Marc Mézard, Lenka Zdeborová
Understanding and quantifying the dynamics of disordered out-of-equilibrium models is an important problem in many branches of science. Using the dynamic cavity method on time traj…
Phase transitions and sample complexity in Bayes-optimal matrix factorization
Yoshiyuki Kabashima, Florent Krzakala, Marc Mézard +2
We analyse the matrix factorization problem. Given a noisy measurement of a product of two matrices, the problem is to estimate back the original matrices. It arises in many applic…