Skip to Main content Skip to Navigation
Conference papers

Classification Asymptotics in the Random Matrix Regime

Abstract : This article discusses the asymptotic performance of classical machine learning classification methods (from discriminant analysis to neural networks) for simultaneously large and numerous Gaussian mixture modelled data. We first provide theoretical bounds on the minimally discriminable class means and covariances under an oracle setting, which are then compared to recent theoretical findings on the performance of machine learning. Non-obvious phenomena are discussed, among which surprising phase transitions in the optimal performance rates for specific hyperparameter settings.
Complete list of metadatas
Contributor : Romain Couillet <>
Submitted on : Monday, December 17, 2018 - 3:01:54 PM
Last modification on : Wednesday, May 13, 2020 - 4:30:06 PM



Romain Couillet, Zhenyu Liao, Xiaoyi Mai. Classification Asymptotics in the Random Matrix Regime. 26th European Signal Processing Conference (EUSIPCO 2018), Sep 2018, Rome, Italy. ⟨10.23919/eusipco.2018.8553034⟩. ⟨hal-01957686⟩



Record views