Learning without concentration for general loss functions
We study the performance of empirical risk minimization in prediction and estimation problems that are carried out in a convex class and relative to a sufficiently smooth convex loss function. The framework is based on the small-ball method and thus is suited for heavy-tailed problems. Moreover, among its outcomes is that a well-chosen loss, calibrated to fit the noise level of the problem, negates some of the ill-effects of outliers and boosts the confidence level—leading to a gaussian like...[Show more]
|Collections||ANU Research Publications|
|Source:||Probability Theory and Related Fields|
|01_Mendelson_Learning_without_concentration_2018.pdf||716.4 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.