Pierre Mergny — accepted AI-conference papers

2025

Optimal Spectral Transitions in High-Dimensional Multi-Index Models

Leonardo Defilippis, Yatin Dandi, Pierre Mergny, Florent Krzakala, Bruno Loureiro

NeurIPS 2025poster

We consider the problem of how many samples from a Gaussian multi-index model are required to weakly reconstruct the relevant index subspace. Despite its increasing popularity as a testbed for investigating the computational complexity of neural networks, results beyond the single-index setting rema…

Cited by 0 Source ↗Scholar ↗

2024

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models

Pierre Mergny, Justin Ko, Florent Krzakala

ICML 2024poster

We discuss the inhomogeneous Wigner spike model, a theoretical framework recently introduced to study structured noise in various learning scenarios, through the prism of random matrix theory, with a specific focus on its spectral properties. Our primary objective is to find an optimal spectral meth…

Cited by 1 Source ↗PDF ↗Scholar ↗