Date
Tue, 18 Feb 2020
Time
15:30 - 16:30
Location
L6
Speaker
Cosme Louart
Organisation
Univ. Grenoble Alpes

This presentation introduces a rigorous framework for the study of commonly used machine learning techniques (kernel methods, random feature maps, etc.) in the regime of large dimensional and numerous data. Exploiting the fact that very realistic data can be modeled by generative models (such as GANs), which are theoretically concentrated random vectors, we introduce a joint random matrix and concentration of measure theory for data processing. Specifically, we present fundamental random matrix results for concentrated random vectors, which we apply to the performance estimation of spectral clustering on real image datasets.

Please contact us with feedback and comments about this page. Last updated on 20 Aug 2022 22:09.