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

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2007.07449
41
12
v1v2 (latest)

Downsampling for Testing and Learning in Product Distributions

15 July 2020
Nathaniel Harms
Yuichi Yoshida
ArXiv (abs)PDFHTML
Abstract

We study distribution-free property testing and learning problems where the unknown probability distribution is a product distribution over Rd\mathbb{R}^dRd. For many important classes of functions, such as intersections of halfspaces, polynomial threshold functions, convex sets, and kkk-alternating functions, the known algorithms either have complexity that depends on the support size of the distribution, or are proven to work only for specific examples of product distributions. We introduce a general method, which we call downsampling, that resolves these issues. Downsampling uses a notion of "rectilinear isoperimetry" for product distributions, which further strengthens the connection between isoperimetry, testing, and learning. Using this technique, we attain new efficient distribution-free algorithms under product distributions on Rd\mathbb{R}^dRd: 1. A simpler proof for non-adaptive, one-sided monotonicity testing of functions [n]d→{0,1}[n]^d \to \{0,1\}[n]d→{0,1}, and improved sample complexity for testing monotonicity over unknown product distributions, from O(d7)O(d^7)O(d7) [Black, Chakrabarty, & Seshadhri, SODA 2020] to O~(d3)\widetilde O(d^3)O(d3). 2. Polynomial-time agnostic learning algorithms for functions of a constant number of halfspaces, and constant-degree polynomial threshold functions. 3. An exp⁡(O(dlog⁡(dk)))\exp(O(d \log(dk)))exp(O(dlog(dk)))-time agnostic learning algorithm, and an exp⁡(O(dlog⁡(dk)))\exp(O(d \log(dk)))exp(O(dlog(dk)))-sample tolerant tester, for functions of kkk convex sets; and a 2O~(d)2^{\widetilde O(d)}2O(d) sample-based one-sided tester for convex sets. 4. An exp⁡(O~(kd))\exp(\widetilde O(k \sqrt d))exp(O(kd​))-time agnostic learning algorithm for kkk-alternating functions, and a sample-based tolerant tester with the same complexity.

View on arXiv
Comments on this paper