Saved in:
Bibliographic Details
Main Author: Sharma, Shivam
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.14308
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We obtain error approximation bounds between expected suprema of canonical processes that are generated by random vectors with independent coordinates and expected suprema of Gaussian processes. In particular, we obtain a sharper proximity estimate for Rademacher and Gaussian complexities. Our estimates are dimension-free, and depend only on the geometric parameters and the numerical complexity of the underlying index set.