Publications

Up-to-date full list of publications of L. Zdeborová is available on Google Scholar.

Warning

Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.

2024

Topics in statistical physics of high-dimensional machine learning

H. C. Cui / L. Zdeborová (Dir.)

Lausanne, EPFL, 2024.

Publications

Up-to-date full list of publications of L. Zdeborová is available on Google Scholar.

2024

Topics in statistical physics of high-dimensional machine learning

2023

Multi-layer state evolution under random convolutional design

Neural-prior stochastic block model

Backtracking Dynamical Cavity Method

Theoretical characterization of uncertainty in high-dimensional linear classification

Learning curves for the multi-class teacher-student perceptron

Bayesian reconstruction of memories stored in neural networks from their connectivity

Error scaling laws for kernel classification under source and capacity conditions

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Expectation consistency for calibration of neural networks

On double-descent in uncertainty quantification in overparametrized models

Tree-AMP: Compositional Inference with Tree Approximate Message Passing

2022

Disordered systems insights on computational hardness

Planted XY model: Thermodynamics and inference

Planted matching problems on random hypergraphs

Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*

(Dis)assortative partitions on random regular graphs

Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising

Aligning random graphs with a sub-tree similarity message-passing algorithm

Large deviations of semisupervised learning in the stochastic block model

Probing transfer learning with a model of synthetic correlated datasets

Multi-layer State Evolution Under Random Convolutional Design

Subspace clustering in high-dimensions: Phase transitions & Statistical-to-Computational gap

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Optimal denoising of rotationally invariant rectangular matrices

2021

Solvable Model for Inheriting the Regularization through Knowledge Distillation

The Gaussian equivalence of generative models for learning with shallow neural networks

Generalisation error in learning with random features and the hidden manifold model*

Stochasticity helps to navigate rough landscapes: comparing gradient-descent-based algorithms in the phase retrieval problem

Construction of optimal spectral methods in phase retrieval

Epidemic mitigation by statistical inference from contact tracing data

Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeed

The planted k-factor problem

Learning Gaussian Mixtures with Generalized Linear Models: Precise Asymptotics in High-dimensions

Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime

Large deviations in the perceptron model and consequences for active learning

Learning curves of generic features maps for realistic datasets with a teacher-student model

2020

Machine learning and statistical physics: preface

The Spiked Matrix Model With Generative Priors

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions

Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization

Phase retrieval in high dimensions: Statistical and computational phase transitions

Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval

Generalized approximate survey propagation for high-dimensional estimation