Xiaoyi MAI
Xiaoyi MAI
L2S, CentraleSupélec, Université de Paris-Saclay
Adresse e-mail validée de l2s.centralesupelec.fr
Titre
Citée par
Citée par
Année
A random matrix analysis and improvement of semi-supervised learning for large dimensional data
X Mai, R Couillet
The Journal of Machine Learning Research 19 (1), 3074-3100, 2018
282018
Classification asymptotics in the random matrix regime
R Couillet, Z Liao, X Mai
2018 26th European Signal Processing Conference (EUSIPCO), 1875-1879, 2018
162018
A large scale analysis of logistic regression: Asymptotic performance and new insights
X Mai, Z Liao, R Couillet
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
122019
High dimensional classification via empirical risk minimization: Improvements and optimality
X Mai, Z Liao
arXiv preprint arXiv:1905.13742, 2019
42019
Statistical analysis and improvement of large dimensional svm
X Mai, R Couillet
private communication, 2018
42018
The counterintuitive mechanism of graph-based semi-supervised learning in the big data regime
X Mai, R Couillet
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
42017
Revisiting and improving semi-supervised learning: a large dimensional approach
X Mai, R Couillet
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
22019
Random Matrix-Inspired Improved Semi-Supervised Learning on Graphs
X Mai, R Couillet
International Conference on Machine Learning, 2018
22018
Consistent Semi-Supervised Graph Regularization for High Dimensional Data
X Mai, R Couillet
arXiv preprint arXiv:2006.07575, 2020
2020
Méthodes des matrices aléatoires pour l’apprentissage en grandes dimensions
X Mai
Paris Saclay, 2019
2019
Methods of random matrices for large dimensional statistical learning
X Mai
Université Paris-Saclay, 2019
2019
Semi-supervised Spectral Clustering
MAI Xiaoyi, R Couillet
2018 52nd Asilomar Conference on Signals, Systems, and Computers, 2012-2016, 2018
2018
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–12