Efficient Agnostic Learning with Average Smoothness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hanneke, Steve, Kontorovich, Aryeh, Kornowski, Guy
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910328185421824
author Hanneke, Steve
Kontorovich, Aryeh
Kornowski, Guy
author_facet Hanneke, Steve
Kontorovich, Aryeh
Kornowski, Guy
contents We study distribution-free nonparametric regression following a notion of average smoothness initiated by Ashlagi et al. (2021), which measures the "effective" smoothness of a function with respect to an arbitrary unknown underlying distribution. While the recent work of Hanneke et al. (2023) established tight uniform convergence bounds for average-smooth functions in the realizable case and provided a computationally efficient realizable learning algorithm, both of these results currently lack analogs in the general agnostic (i.e. noisy) case. In this work, we fully close these gaps. First, we provide a distribution-free uniform convergence bound for average-smoothness classes in the agnostic setting. Second, we match the derived sample complexity with a computationally efficient agnostic learning algorithm. Our results, which are stated in terms of the intrinsic geometry of the data and hold over any totally bounded metric space, show that the guarantees recently obtained for realizable learning of average-smooth functions transfer to the agnostic setting. At the heart of our proof, we establish the uniform convergence rate of a function class in terms of its bracketing entropy, which may be of independent interest.
format Preprint
id arxiv_https___arxiv_org_abs_2309_17016
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Efficient Agnostic Learning with Average Smoothness
Hanneke, Steve
Kontorovich, Aryeh
Kornowski, Guy
Machine Learning
Statistics Theory
We study distribution-free nonparametric regression following a notion of average smoothness initiated by Ashlagi et al. (2021), which measures the "effective" smoothness of a function with respect to an arbitrary unknown underlying distribution. While the recent work of Hanneke et al. (2023) established tight uniform convergence bounds for average-smooth functions in the realizable case and provided a computationally efficient realizable learning algorithm, both of these results currently lack analogs in the general agnostic (i.e. noisy) case. In this work, we fully close these gaps. First, we provide a distribution-free uniform convergence bound for average-smoothness classes in the agnostic setting. Second, we match the derived sample complexity with a computationally efficient agnostic learning algorithm. Our results, which are stated in terms of the intrinsic geometry of the data and hold over any totally bounded metric space, show that the guarantees recently obtained for realizable learning of average-smooth functions transfer to the agnostic setting. At the heart of our proof, we establish the uniform convergence rate of a function class in terms of its bracketing entropy, which may be of independent interest.
title Efficient Agnostic Learning with Average Smoothness
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2309.17016