Résumé : Machine learning theoretical models very often assume a dataset obtained from a Gaussian distribution, or from a Gaussian mixture. The possible limitations of such a Gaussian assumption have been recently object of investigation, and theoretically characterization, leading to a number of "Gaussian universality" results. In this talk I will present an analytical treatment of the performance in high dimensions of simple architectures on heavy-tailed distributed datasets, showing that even simple generalized linear models exhibit a striking dependence on non-Gaussian features in both classification and regression tasks.

 [Slides.pdf] [arXiv] [arXiv]

Dernière modification : Thursday 21 November 2024

Contact pour cette page : Cyril.Banderier at lipn.univ-paris13.fr