Cosme Louart

Cosme Louart

Phd Student in machine learning

Publications

2022

C Louart, R Couillet, “A Concentration of Measure and Random Matrix Approach to Large Dimensional Robust Statistics”, accepted by The Annals of Applied Probability [arXiv]

2021

C.Louart, R.Couillet, “Spectral properties of sample covariance matrices arising from random matrices with independent non identically distributed columns “, submitted to RMTA. [paper].

MEA.Seddik, C.Louart, R.Couillet, M.Tamaazousti, “The Unexpected Deterministic and Universal Behavior of Large Softmax Classifiers”, AISTATS’2021. [paper] [bibtex][github][interactive julia code (takes some minuts to charge)].

C Louart, R. Couillet, “Concentration of measure and generalized product of random vectors with an application to Hanson-Wright-like inequalities.” submitted to Electronic Journal of Probability [arXiv] [paper].

2020

MEA.Seddik, C.Louart, M.Tamaazousti, R.Couillet, “Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures”, ICML’2020. [paper] [arxiv] [slides] [bibtex].

2019

C Louart, R Couillet, “Concentration of Measure and Large Random Matrices with an application to Sample Covariance Matrices”, arXiv preprint arXiv:1805.08295 (2019) [arXiv] [paper].

M Tiomoko, C Louart, R Couillet, “Large Dimensional Asymptotics of Multi-task Learning”, IEEE International Conference on Acoustics, Speech and Signal Processings (ICASSP’19) [paper].

C. Louart, R. Couillet, “A concentration of measure perspective to robust statistics”, IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP’19)[paper].

2018

C Louart, Z Liao, R Couillet, “A random matrix approach to neural networks”, The Annals of Applied Probability 28 (2), 1190-1248 [paper].

C Louart, R Couillet, “A Random Matrix and Concentration Inequalities Framework for Neural Networks Analysis” IEEE International Conference on Acoustics, Speech and Signal Processings (ICASSP’18) [paper].

2017

C Louart, R Couillet, “Harnessing neural networks: A random matrix approach”, IEEE International Conference on Acoustics, Speech and Signal Processings (ICASSP’17) [paper].