Xiaoyi MAI

Xiaoyi MAI

Postdoc, CRIStAL, CNRS

Preprints

  1. Mai, X., & Rémi, B. (2022). Un processus ponctuel déterminantal pour la sélection de variables supervisée.
    paper
  2. Mai, X., & Liao, Z. (2020). High dimensional classification via regularized and unregularized empirical risk minimization: precise error and optimal loss.
    paper

Journal articles

  1. Mai, X., & Couillet, R. (2021). Consistent semi-supervised graph regularization for high dimensional data. The Journal of Machine Learning Research, 22(94), 1–48.
    paper
  2. Mai, X., & Couillet, R. (2018). A random matrix analysis and improvement of semi-supervised learning for large dimensional data. The Journal of Machine Learning Research, 19(1), 3074–3100.
    paper

Conference papers

  1. Mai, X., Avestimehr, S., Ortega, A., & Soltanolkotabi, M. (2022). On the effectiveness of active learning by uncertainty sampling in classification of Gaussian mixture data. (Accepted) 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
    paper
  2. Mai, X., Liao, Z., & Couillet, R. (2019). A large scale analysis of logistic regression: Asymptotic performance and new insights. 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3357–3361.
    paper
  3. Mai, X., & Couillet, R. (2019). Revisiting and improving semi-supervised learning: a large dimensional approach. 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3547–3551.
    paper
  4. Couillet, R., Liao, Z., & Mai, X. (2018). Classification asymptotics in the random matrix regime. 2018 26th European Signal Processing Conference (EUSIPCO), 1875–1879.
    paper
  5. Mai, X., & Couillet, R. (2018). Semi-Supervised Spectral Clustering. 2018 52nd Asilomar Conference on Signals, Systems, and Computers, 2012–2016.
    paper
  6. Mai, X., & Couillet, R. (2017). The counterintuitive mechanism of graph-based semi-supervised learning in the big data regime. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2821–2825.
    paper

Thesis

  1. Mai, X. (2019). Methods of random matrices for large dimensional statistical learning. Université Paris-Saclay.
    paper