Antoine Maillard

collaborators

6 papers

stat.ML2026

Memorisation, convergence and generalisation in generative models

Antoine Maillard, Sebastian Goldt

Generative neural networks learn how to produce highly realistic images from a large, but finite number of examples - or do they simply memorise their training set? To settle this…

stat.ML2026

Factual recall in linear associative memories: sharp asymptotics and mechanistic insights

Alessio Giorlandino, Sebastian Goldt, Antoine Maillard

Large language models demonstrate remarkable ability in factual recall, yet the fundamental limits of storing and retrieving input--output associations with neural networks remain…

stat.ML2026

A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models

Leonardo Defilippis, Florent Krzakala, Bruno Loureiro +1

Understanding when learning is statistically possible yet computationally hard is a central challenge in high-dimensional statistics. In this work, we investigate this question in…

math.PR2025

Average-case matrix discrepancy: satisfiability bounds

Antoine Maillard

Given a sequence of $d \times d$ symmetric matrices ${W_{i}}_{i = 1}^{n}$ , and a margin $I^ > 0$ , we investigate whether it is possible to find signs $(Îµ_1, \dots, Îµ_n) \in \…

math.PR2025

Exact threshold for approximate ellipsoid fitting of random points

Afonso S. Bandeira, Antoine Maillard

We consider the problem $(P)$ of exactly fitting an ellipsoid (centered at $0$ ) to $n$ standard Gaussian random vectors in $R^{d}$ , as $n, d \to \infty$ with $n / d^2 \t…

math.PR2025

Randomstrasse101: Open Problems of 2024

Afonso S. Bandeira, Anastasia Kireeva, Antoine Maillard +1

$Randomstrasse101$ is a blog dedicated to Open Problems in Mathematics, with a focus on Probability Theory, Computation, Combinatorics, Statistics, and related topics. Thi…