Reliable Learning of Halfspaces under Gaussian Marginals

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Diakonikolas, Ilias, Ren, Lisheng, Zarifis, Nikos
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929595094138880
author Diakonikolas, Ilias
Ren, Lisheng
Zarifis, Nikos
author_facet Diakonikolas, Ilias
Ren, Lisheng
Zarifis, Nikos
contents We study the problem of PAC learning halfspaces in the reliable agnostic model of Kalai et al. (2012). The reliable PAC model captures learning scenarios where one type of error is costlier than the others. Our main positive result is a new algorithm for reliable learning of Gaussian halfspaces on $\mathbb{R}^d$ with sample and computational complexity $$d^{O(\log (\min\{1/α, 1/ε\}))}\min (2^{\log(1/ε)^{O(\log (1/α))}},2^{\mathrm{poly}(1/ε)})\;,$$ where $ε$ is the excess error and $α$ is the bias of the optimal halfspace. We complement our upper bound with a Statistical Query lower bound suggesting that the $d^{Ω(\log (1/α))}$ dependence is best possible. Conceptually, our results imply a strong computational separation between reliable agnostic learning and standard agnostic learning of halfspaces in the Gaussian setting.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11238
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reliable Learning of Halfspaces under Gaussian Marginals
Diakonikolas, Ilias
Ren, Lisheng
Zarifis, Nikos
Machine Learning
Data Structures and Algorithms
We study the problem of PAC learning halfspaces in the reliable agnostic model of Kalai et al. (2012). The reliable PAC model captures learning scenarios where one type of error is costlier than the others. Our main positive result is a new algorithm for reliable learning of Gaussian halfspaces on $\mathbb{R}^d$ with sample and computational complexity $$d^{O(\log (\min\{1/α, 1/ε\}))}\min (2^{\log(1/ε)^{O(\log (1/α))}},2^{\mathrm{poly}(1/ε)})\;,$$ where $ε$ is the excess error and $α$ is the bias of the optimal halfspace. We complement our upper bound with a Statistical Query lower bound suggesting that the $d^{Ω(\log (1/α))}$ dependence is best possible. Conceptually, our results imply a strong computational separation between reliable agnostic learning and standard agnostic learning of halfspaces in the Gaussian setting.
title Reliable Learning of Halfspaces under Gaussian Marginals
topic Machine Learning
Data Structures and Algorithms
url https://arxiv.org/abs/2411.11238