ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2405.09312
43
6

Agnostic Active Learning of Single Index Models with Linear Sample Complexity

15 May 2024
Aarshvi Gajjar
Wai Ming Tai
Xingyu Xu
Chinmay Hegde
Yi Li
Chris Musco
ArXivPDFHTML
Abstract

We study active learning methods for single index models of the form F(x)=f(⟨w,x⟩)F({\mathbf x}) = f(\langle {\mathbf w}, {\mathbf x}\rangle)F(x)=f(⟨w,x⟩), where f:R→Rf:\mathbb{R} \to \mathbb{R}f:R→R and x,w∈Rd{\mathbf x,\mathbf w} \in \mathbb{R}^dx,w∈Rd. In addition to their theoretical interest as simple examples of non-linear neural networks, single index models have received significant recent attention due to applications in scientific machine learning like surrogate modeling for partial differential equations (PDEs). Such applications require sample-efficient active learning methods that are robust to adversarial noise. I.e., that work even in the challenging agnostic learning setting. We provide two main results on agnostic active learning of single index models. First, when fff is known and Lipschitz, we show that O~(d)\tilde{O}(d)O~(d) samples collected via {statistical leverage score sampling} are sufficient to learn a near-optimal single index model. Leverage score sampling is simple to implement, efficient, and already widely used for actively learning linear models. Our result requires no assumptions on the data distribution, is optimal up to log factors, and improves quadratically on a recent O(d2){O}(d^{2})O(d2) bound of \cite{gajjar2023active}. Second, we show that O~(d)\tilde{O}(d)O~(d) samples suffice even in the more difficult setting when fff is \emph{unknown}. Our results leverage tools from high dimensional probability, including Dudley's inequality and dual Sudakov minoration, as well as a novel, distribution-aware discretization of the class of Lipschitz functions.

View on arXiv
Comments on this paper