[SFdS] Information du groupe BFA
WG Risk - Thursday January 13, 2022 - Prof. Mohamed NDAOUD

Dear All,

We have the pleasure thanks to the support of the ESSEC IDS dpt, Institut des Actuaires, LabEx MME-DII, the group BFA (SFdS), to invite you to the seminar by:

Prof. Mohamed NDAOUD
Chair of Excellence in Data Science (CY Initiative)
IDS Department, ESSEC Business School

Date: Thursday, January 13 at 12:30 pm (Paris) and 7:30 pm (Singapore)

Dual format: ESSEC Paris La Défense (CNIT), Amphi 201, and via Zoom, please click here
(Password/Code : WGRisk)

« On potential benefits of overfitting in high dimensions »

We consider the supervised clustering problem under the two-component anisotropic Gaussian mixture model in high dimensions and in the non-asymptotic setting. We characterize precisely the risk of l2 regularized supervised least squares classifiers. We deduce the fact that the interpolating solution may outperform regularized classifiers, under mild assumptions on the covariance structure of the noise. Our analysis also shows that overfitting can be robust to corruption in the covariance of the noise when the signal is aligned with the "clean'' part of the covariance, for the properly defined notion of alignment. To the best of our knowledge, this peculiar phenomenon has not yet been investigated in the rapidly growing literature related to interpolation. We conclude that overfitting is not only benign but can also be robust.
This is joint work with Stanislav Minsker and Yiqiu Shen.

Kind regards,
Jeremy Heng, Olga Klopp and Marie Kratz
and Riada Djebbar (Singapore Actuarial Society - ERM)

SFdS - Société Française de Statistique
©2022 SFdS