[Statlist] Research Webinar in Statistics *FRIDAY, 5 MARCH 2021* GSEM, University of Geneva

[gsem-support-instituts]

Dear All,

We are pleased to invite you to our next Research Webinar.

Looking forward to seeing you


Organizers :                                                                                   
E. Cantoni - S. Engelke - D. La Vecchia - E. Ronchetti
S. Sperlich - F. Trojani - M.-P. Victoria-Feser


FRIDAY, 5 MARCH 2021 at 11:15am
ONLINE
Please join the Zoom research webinar: https://unige.zoom.us/j/92924332087?pwd=U1U1NFk4dTFCRHBMeWYrSDBQcXBiQT09
Meeting ID: 929 2433 2087
Passcode: 399192


M-Estimation and Median of Means for Robust Machine Learning
Timothée MATHIEU (https://www.imo.universite-paris-saclay.fr/~mathieu/assets/cv.pdf ) - Paris-Saclay University, France

ABSTRACT:
Most machine learning algorithms are not robust as their predictive power can be highly disturbed by a small amount of abnormal data. In this talk I will show how to use some robust estimators of the mean to construct a robust risk minimization framework for machine learning tasks like classification or regression. Particularly, I will first present some finite sample results (i.e. concentration inequalities) on M-estimators and Median of Means when estimating the mean, then I will use these estimators to construct robust Machine Learning algorithms and finally I will show illustrations of these algorithms in several Machine Learning application.


Visit the website: https://www.unige.ch/gsem/en/research/seminars/rcs/