57 citations · 188 across the 14 of their papers we have counts for
14 papers
Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
Davide Ghio, Yatin Dandi, Florent Krzakala +1
Recent years witnessed the development of powerful generative models based on flows, diffusion or autoregressive neural networks, achieving remarkable success in generating data fr…
Estimating rank-one matrices with mismatched prior and noise: universality and large deviations
Alice Guionnet, Justin Ko, Florent Krzakala +1
We prove a universality result that reduces the free energy of rank-one matrix estimation problems in the setting of mismatched prior and noise to the computation of the free energ…
Gibbs Sampling the Posterior of Neural Networks
Giovanni Piccioli, Emanuele Troiani, Lenka Zdeborová
In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation i…
High-dimensional Asymptotics of Denoising Autoencoders
Hugo Cui, Lenka Zdeborová
We address the problem of denoising data from a Gaussian mixture using a two-layer non-linear autoencoder with tied weights and a skip connection. We consider the high-dimensional…
Maximally-stable Local Optima in Random Graphs and Spin Glasses: Phase Transitions and Universality
Yatin Dandi, David Gamarnik, Lenka Zdeborová
We consider -stable local optima of Ising spin glass models, defined as spin configurations such that for nearly all of the spins, flipping their values results in increasing en…
Backtracking Dynamical Cavity Method
Freya Behrens, Barbora Hudcová, Lenka Zdeborová
The cavity method is one of the cornerstones of the statistical physics of disordered systems such as spin glasses and other complex systems. It is able to analytically and asympto…
Statistical mechanics of the maximum-average submatrix problem
Vittorio Erba, Florent Krzakala, Rodrigo Pérez +1
We study the maximum-average submatrix problem, in which given an matrix one needs to find the submatrix with the largest average of entries. We study…
Expectation consistency for calibration of neural networks
Lucas Clarté, Bruno Loureiro, Florent Krzakala +1
Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient cal…
Universality laws for Gaussian mixtures in generalized linear models
Yatin Dandi, Ludovic Stephan, Florent Krzakala +2
Let denote independent samples from a general mixture distribution , and consider the hypothesis class of gener…
Bayes-optimal Learning of Deep Random Networks of Extensive-width
Hugo Cui, Florent Krzakala, Lenka Zdeborová
We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic l…
Gaussian Universality of Perceptrons with Random Labels
Federica Gerace, Florent Krzakala, Bruno Loureiro +2
While classical in many theoretical settings - and in particular in statistical physics-inspired works - the assumption of Gaussian i.i.d. input data is often perceived as a strong…
Following Gibbs States Adiabatically - The Energy Landscape of Mean Field Glassy Systems
Florent Krzakala, Lenka Zdeborová
We introduce a generalization of the cavity, or Bethe-Peierls, method that allows to follow Gibbs states when an external parameter, e.g. the temperature, is adiabatically changed.…
Potts Glass on Random Graphs
Florent Krzakala, Lenka Zdeborová
We solve the q-state Potts model with anti-ferromagnetic interactions on large random lattices of finite coordination. Due to the frustration induced by the large loops and to the…
Thermodynamic origin of order parameters in mean-field models of spin glasses
V. Janis, L. Zdeborova
We analyze thermodynamic behavior of general -component mean-field spin glass models in order to identify origin of the hierarchical structure of the order parameters from the r…