Covering numbers for bounded variation functions
Prerona Dutta, Khai T. Nguyen

TL;DR
This paper investigates the minimal number of bounded variation functions needed to approximate any such function within a specified accuracy in the L^1 norm, providing bounds on this covering number.
Contribution
It introduces upper and lower bounds for covering numbers of bounded variation functions in the L^1 metric, advancing understanding of their approximation complexity.
Findings
Established bounds on covering numbers for bounded variation functions.
Quantified the approximation complexity in terms of epsilon.
Provided theoretical estimates for function representation.
Abstract
In this paper, we provide upper and lower estimates for the minimal number of functions needed to represent a bounded variation function with an accuracy of epsilon with respect to -distance.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
