1.3k citations · 3.3k across the 48 of their papers we have counts for
53 papers
Optimal Data Splitting for Holdout Cross-Validation in Large Covariance Matrix Estimation
Lamia Lamrani, Christian Bongiorno, Marc Potters
Cross-validation is a statistical tool that can be used to improve large covariance matrix estimation. Although its efficiency is observed in practical applications and a convergen…
Distribution of the Diagonal Entries of the Resolvent of a Complex Ginibre Matrix
Pierre Bousseyroux, Jean-Philippe Bouchaud, Marc Potters
The study of eigenvalue distributions in random matrix theory is often conducted by analyzing the resolvent matrix $ \mathbf{G}_{\mathbf{M}}^N(z) = (z \mathbf{1} - \mathbf{M})^{-1}…
Spectral Initialization for High-Dimensional Phase Retrieval with Biased Spatial Directions
Pierre Bousseyroux, Marc Potters
We explore a spectral initialization method that plays a central role in contemporary research on signal estimation in nonconvex scenarios. In a noiseless phase retrieval framework…
Excess Out-of-Sample Risk and Fleeting Modes
Jean-Philippe Bouchaud, Iacopo Mastromatteo, Marc Potters +1
Using Random Matrix Theory, we propose a universal and versatile tool to reveal the existence of "fleeting modes", i.e. portfolios that carry statistically significant excess risk,…
Right large deviation principle for the top eigenvalue of the sum or product of invariant random matrices
Pierre Mergny, Marc Potters
In this note we study the right large deviation of the top eigenvalue (or singular value) of the sum or product of two random matrices and as their dimens…
Rank one HCIZ at high temperature: interpolating between classical and free convolutions
Pierre Mergny, Marc Potters
We study the rank one Harish-Chandra-Itzykson-Zuber integral in the limit where , called the high temperature regime and show that it can be used to construct…