BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:On the Role of Gaussian Covariates in Minimum Norm Interpolation
DTSTART:20250516T151500
DTEND:20250516T161500
DTSTAMP:20260521T043328Z
UID:330f561b612c96613479bb42b0ae632e6023f675aa52ffd4027fcfe3
CATEGORIES:Conferences - Seminars
DESCRIPTION:Gil Kur\, ETH Zurich\nIn the literature on benign overfitting 
 in linear models\, also referred to as minimum norm interpolation\, it is 
 typically assumed that the covariates follow a Gaussian distribution. 
 Existing proofs heavily rely on the Gaussian Minimax Theorem (GMT)\, mak
 ing them inapplicable to other distributions in the linear setting.\nIn ou
 r work\, we are the first to establish matching rates for sub-Gaussian co
 variates in $\\ell_p$-linear regression through a novel approach inspired
  by modern functional analysis.\nIn this talk\, we provide an overview of 
 this proof and explore the role of Gaussian covariates in benign overfi
 tting from a purely geometric perspective.
LOCATION:CM 1 517 https://plan.epfl.ch/?room==CM%201%20517
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR