Saved in:
Bibliographic Details
Main Authors: Li, Yi, Tai, Wai Ming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.18213
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910844004073472
author Li, Yi
Tai, Wai Ming
author_facet Li, Yi
Tai, Wai Ming
contents The active regression problem of the single-index model is to solve $\min_x \lVert f(Ax)-b\rVert_p$, where $A$ is fully accessible and $b$ can only be accessed via entry queries, with the goal of minimizing the number of queries to the entries of $b$. When $f$ is Lipschitz, previous results only obtain constant-factor approximations. This work presents the first algorithm that provides a $(1+\varepsilon)$-approximation solution by querying $\tilde{O}(d^{\frac{p}{2}\vee 1}/\varepsilon^{p\vee 2})$ entries of $b$. This query complexity is also shown to be optimal up to logarithmic factors for $p\in [1,2]$ and the $\varepsilon$-dependence of $1/\varepsilon^p$ is shown to be optimal for $p>2$.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18213
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Near-optimal Active Regression of Single-Index Models
Li, Yi
Tai, Wai Ming
Data Structures and Algorithms
Machine Learning
The active regression problem of the single-index model is to solve $\min_x \lVert f(Ax)-b\rVert_p$, where $A$ is fully accessible and $b$ can only be accessed via entry queries, with the goal of minimizing the number of queries to the entries of $b$. When $f$ is Lipschitz, previous results only obtain constant-factor approximations. This work presents the first algorithm that provides a $(1+\varepsilon)$-approximation solution by querying $\tilde{O}(d^{\frac{p}{2}\vee 1}/\varepsilon^{p\vee 2})$ entries of $b$. This query complexity is also shown to be optimal up to logarithmic factors for $p\in [1,2]$ and the $\varepsilon$-dependence of $1/\varepsilon^p$ is shown to be optimal for $p>2$.
title Near-optimal Active Regression of Single-Index Models
topic Data Structures and Algorithms
Machine Learning
url https://arxiv.org/abs/2502.18213