Volume 133, Number 2, January 2021
|Number of page(s)||7|
|Published online||23 March 2021|
Large deviations of extreme eigenvalues of generalized sample covariance matrices
Laboratoire de Physique de l'École Normale Supérieure, ENS, Université PSL - Paris, France
Received: 2 September 2020
Accepted: 9 December 2020
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 .
PACS: 02.50.Cw – Probability theory / 75.10.Nr – Spin-glass and other random models / 05.90.+m – Other topics in statistical physics, thermodynamics, and nonlinear dynamical systems (restricted to new topics in section 05)
© 2021 EPLA
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.