activity
20232025
collaborators

10 papers

stat.ML2025

The Computational Advantage of Depth: Learning High-Dimensional Hierarchical Functions with Gradient Descent

Yatin Dandi, Luca Pesce, Lenka Zdeborová +1

Understanding the advantages of deep neural networks trained by gradient descent (GD) compared to shallow models remains an open theoretical challenge. In this paper, we introduce…

cond-mat.dis-nn2024

Quenches in the Sherrington-Kirkpatrick model

Vittorio Erba, Freya Behrens, Florent Krzakala +1

The Sherrington-Kirkpatrick (SK) model is a prototype of a complex non-convex energy landscape. Dynamical processes evolving on such landscapes and locally aiming to reach minima a…

stat.ML2024

Fundamental limits of Non-Linear Low-Rank Matrix Estimation

Pierre Mergny, Justin Ko, Florent Krzakala +1

We consider the task of estimating a low-rank matrix from non-linear and noisy observations. We prove a strong universality result showing that Bayes-optimal performances are chara…

stat.ML2024

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression

Lucas Clarté, Adrien Vandenbroucque, Guillaume Dalle +3

We investigate popular resampling methods for estimating the uncertainty of statistical models, such as subsampling, bootstrap and the jackknife, and their performance in high-dime…

stat.ML2024

Asymptotics of feature learning in two-layer networks after one gradient-step

Hugo Cui, Luca Pesce, Yatin Dandi +4

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single grad…

cs.LG2024

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Hugo Cui, Freya Behrens, Florent Krzakala +1

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of t…