Recent & Upcoming Events

More Talks

Two Long talks at ICML 2018
Jul 10, 2018 12:00 AM
Ph.D. Mid-Term Evaluation
Mar 19, 2018 12:00 AM

Publications

Conferences:

  • X. Mai, Z. Liao, R. Couillet, “A Large Scale Analysis of Logistic Regression: Asymptotic Performance and New Insights”, (submitted to) IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’19), Brighton, UK, 2019. [preprint]

  • R. Couillet, Z. Liao, X. Mai, “Classification Asymptotics in the Random Matrix Regime”, European Signal Processing Conference (EUSIPCO’18), Rome, Italy, 2018. [preprint]

  • Z. Liao, R. Couillet, “On the Spectrum of Random Features Maps of High Dimensional Data”, The 35th International Conference on Machine Learning (ICML’18), Stockholm, Sweden, 2018. [preprint] [slides]

  • Z. Liao, R. Couillet, “The Dynamics of Learning: A Random Matrix Approach”, The 35th International Conference on Machine Learning (ICML’18), Stockholm, Sweden, 2018. [preprint] [slides]

  • Z. Liao, R. Couillet, “Une Analyse des Méthodes de Projections Aléatoires par la Théorie des Matrices Aléatoires”, Colloque GRETSI’17, Juan Les Pins, France, 2017. [preprint] [slides]

  • Z. Liao, R. Couillet, “Random Matrices Meet Machine Learning: A Large Dimensional Analysis of LS-SVM”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’17), New Orleans, USA, 2017. [preprint] [slides]

Journals:

  • Y.Chitour, Z. Liao, R. Couillet, “A Geometric Approach of Gradient Descent Algorithms in Neural Networks”. [preprint]

  • C. Louart, Z. Liao, R. Couillet, “A Random Matrix Approach to Neural Networks”, The Annals of Applied Probability 28 (2), 1190-1248. [preprint]

  • Z. Liao, R. Couillet, “A Large Dimensional Analysis of Least Squares Support Vector Machines”, (submitted to) Journal of Machine Learning Research, 2017. [preprint]

Teaching

I am a teaching assistant at CentraleSupélec, Signal and Statistics department, for the following courses:

  • 2017- 2018: Lab work: Signals and systems 1. Together with Prof. LE BRUSQUET. 54 hours in total.

Contact