Ellipsoid Methods for Metric Entropy Computation
Thomas Allard, Helmut B\"olcskei

TL;DR
This paper introduces a novel ellipsoid-based method for computing the metric entropy of infinite-dimensional ellipsoids, offering a unified approach that improves existing results across various analytic function classes.
Contribution
It develops a new methodology that avoids explicit coverings, providing a unified framework for metric entropy computation of diverse analytic function classes.
Findings
Improves metric entropy bounds for analytic function classes
Provides a unified framework applicable to various function spaces
Enhances understanding of infinite-dimensional ellipsoid properties
Abstract
We present a new methodology for the characterization of the metric entropy of infinite-dimensional ellipsoids with exponentially decaying semi-axes. This procedure does not rely on the explicit construction of coverings or packings and provides a unified framework for the derivation of the metric entropy of a wide variety of analytic function classes, such as periodic functions analytic on a strip, analytic functions bounded on a disk, and functions of exponential type. In each of these cases, our results improve upon the best known results in the literature.
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.
Taxonomy
TopicsModel Reduction and Neural Networks · Matrix Theory and Algorithms
