Showing 2025Show all
3 papers · 1 filter
math.ST2025
Robust, sub-Gaussian mean estimators in metric spaces
Daniel Bartl, Gabor Lugosi, Roberto Imbuzeiro Oliveira +1
Estimating the mean of a random vector from i.i.d. data has received considerable attention, and the optimal accuracy one may achieve with a given confidence is fairly well underst…
math.PR2025
A uniform Dvoretzky-Kiefer-Wolfowitz inequality
Daniel Bartl, Shahar Mendelson
We show that under minimal assumptions on a class of functions defined on a probability space , there is a threshold satisfying the following…
math.ST2025
Do we really need the Rademacher complexities?
Daniel Bartl, Shahar Mendelson
We study the fundamental problem of learning with respect to the squared loss in a convex class. The state-of-the-art sample complexity estimates in this setting rely on Rademacher…