Files in this item



application/pdfCHU-THESIS-2021.pdf (279kB)Restricted to U of Illinois
(no description provided)PDF


Title:Chain rules for Rademacher complexity
Author(s):Chu, Yifeng
Advisor(s):Raginsky, Maxim
Department / Program:Electrical & Computer Eng
Discipline:Electrical & Computer Engr
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Rademacher complexity
Bernoulli process
composite function class
generic chaining
Abstract:Two preliminary estimates are obtained for expected suprema of Bernoulli processes indexed by an image of a bounded Euclidean subset through a class of Lipschitz functions. If that bounded subset is given by the projection of a bounded function class onto a sample vector, the result can be considered as a control over empirical Rademacher complexity of a composite function class. Such an estimate can be applied to learning problems where the hypotheses have composite structure or where more than one function is needed to determine the empirical loss.
Issue Date:2021-07-23
Rights Information:Copyright 2021 Yifeng Chu
Date Available in IDEALS:2022-01-12
Date Deposited:2021-08

This item appears in the following Collection(s)

Item Statistics