cs.DSAug 2, 2026

Active Regression for Single-Index Models with Unknown Link Functions

Authors: Chansophea Wathanak InYi LiWai Ming TaiXuan Wu

Organizations: School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore · Independent Researcher · John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, China

Abstract

This paper studies active regression for single-index models under general p\ell_p-loss with an unknown 11-Lipschitz link function ff, formulated as minf,xf(Ax)bpp\min_{f,x} \|f(Ax)-b\|_p^p with full access to AA but coordinate-query access to bb. Prior work established upper bounds for known link functions for all p1p\geq 1 and for unknown link functions only in the p=2p=2 case, together with lower bounds for p2p\leq 2. This work addresses the more challenging setting of unknown link functions and general p1p \geq 1. A non-adaptive sampling algorithm is presented that achieves a (1+ε)(1+ε)-approximation using O(dp/21/εp2polylog(n/ε))O(d^{p/2\vee 1}/ε^{p\vee 2}\operatorname{poly}\log(n/ε)) queries. Nearly tight lower bounds are also established for p>2p>2. These results close much of the remaining gap in active p\ell_p-regression for single-index models.

Explore similar work

CardsList