ESSEC METALAB

RESEARCH

OPTIMAL ROBUST MEAN AND LOCATION ESTIMATION VIA CONVEX PROGRAMS WITH RESPECT TO ANY PSEUDO-NORMS

[ARTICLE] This paper addresses robust mean and location estimation with respect to any pseudo-norm and improves the entropic minimax lower bound, demonstrating that the Gaussian mean width is the correct statistical complexity measure for this problem.

by Guillaume LECUE (ESSEC Business School), Jules DEPERSIN

We consider the problem of robust mean and location estimation w.r.t. any pseudo-norm of the form x∈ℝd→||x||S=supv∈S<v,x> where S is any symmetric subset of ℝd. We improved the entropic minimax lower bound from [Lugosi and Mendelson, 2019] and closes the gap characterized by Sudakov's inequality between the entropy and the Gaussian mean width for this problem. This shows that the right statistical complexity measure for the mean estimation problem is the Gaussian mean width. We also show that this rate can be achieved by a solution to a convex optimization problem in the adversarial and L2 heavy-tailed setup by considering minimum of some Fenchel-Legendre transforms constructed using the Median-of-means principle. We finally show that this rate may also be achieved in situations where there is not even a first moment but a location parameter exists.

[Please read the research paper here]

Research list
arrow-right
Résumé de la politique de confidentialité

Ce site utilise des cookies afin que nous puissions vous fournir la meilleure expérience utilisateur possible. Les informations sur les cookies sont stockées dans votre navigateur et remplissent des fonctions telles que vous reconnaître lorsque vous revenez sur notre site Web et aider notre équipe à comprendre les sections du site que vous trouvez les plus intéressantes et utiles.