Year: 2018
Type: preprint
Abstract: We establish a tight characterization of the worst-case rates for the excess risk of agnostic learning with sample compression schemes and for uniform convergence for agnostic sample compression schemes. In particular, we find that the optimal rates of convergence for size-$k$ agnostic sample compression schemes are of the form $\sqrt{\frac{k \log(n/k)}{n}}$, which contrasts with agnostic learning with classes of VC dimension $k$, where the optimal rates are of the form $\sqrt{\frac{k}{n}}$.
Source: arXiv (Cornell University)
Authors: Hanneke, Steve, Kontorovich, Aryeh
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2804479917