BIDSA Webinar: "Robust Estimation via M.M.D. Minimization"

Image of BIDSA Webinar: "Robust Estimation via M.M.D. Minimization"
Zoom webinar
Speaker: Pierre Alquier
“Robust Estimation via M.M.D. Minimization”

Pierre Alquier (RIKEN Center for Advanced Intelligence Project)    

April 22, 2021 | 2pm CEST | Zoom

In  this  talk,  I  will  study  the  properties  of  parametric  estimators  based  on  the  Maximum Mean Discrepancy (MMD) defined by Briol et al.  (2019).  In a first time,  I will show that these estimators are universal in the i.i.d setting: even in case of misspecification, they converge to the best approximation of the distribution of the data in the model, without ANY assumption on this model. This leads to very strong robustness properties. In a second time,I will show that these results remain valid when the data is not independent,  but satisfy instead a weak-dependence condition. This condition is based on a new dependence coefficient, which is itself defined thanks to the MMD. I will show through examples that this new notion of dependence is actually quite general.

This talk is based on the following papers and softwares, with Badr-Eddine Chérief Abdellatif (Oxford University), Mathieu Gerber(University of Bristol), Jean-David Fermanian (ENSAE Paris) and Alexis Derumigny (University of Twente):