Large deviations of extreme eigenvalues of generalized sample covariance matrices - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue EPL - Europhysics Letters Année : 2021

Large deviations of extreme eigenvalues of generalized sample covariance matrices

Antoine Maillard
  • Fonction : Auteur
  • PersonId : 1067182

Résumé

We present an analytical technique to compute the probability of rare events in which the largest eigenvalue of a random matrix is atypically large (i.e., the right tail of its large deviations). The results also transfer to the left tail of the large deviations of the smallest eigenvalue. The technique improves upon past methods by not requiring the explicit law of the eigenvalues, and we apply it to a large class of random matrices that were previously out of reach. In particular, we solve an open problem related to the performance of principal components analysis on highly correlated data, and open the way towards analyzing the high-dimensional landscapes of complex inference models. We probe our results using an importance sampling approach, effectively simulating events with probability as small as .

Dates et versions

hal-03186162 , version 1 (30-03-2021)

Identifiants

Citer

Antoine Maillard. Large deviations of extreme eigenvalues of generalized sample covariance matrices. EPL - Europhysics Letters, 2021, 133 (2), pp.20005. ⟨10.1209/0295-5075/133/20005⟩. ⟨hal-03186162⟩
23 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More