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. 1401.7278
111
93
v1v2v3 (latest)

Minimax-optimal nonparametric regression in high dimensions

28 January 2014
Yun Yang
S. Tokdar
ArXiv (abs)PDFHTML
Abstract

Minimax L2L_2L2​ risks for high-dimensional nonparametric regression are derived under two sparsity assumptions: (1) the true regression surface is a sparse function that depends only on d=O(log⁡n)d=O(\log n)d=O(logn) important predictors among a list of ppp predictors, with log⁡p=o(n)\log p=o(n)logp=o(n); (2) the true regression surface depends on O(n)O(n)O(n) predictors but is an additive function where each additive component is sparse but may contain two or more interacting predictors and may have a smoothness level different from other components. For either modeling assumption, a practicable extension of the widely used Bayesian Gaussian process regression method is shown to adaptively attain the optimal minimax rate (up to log⁡n\log nlogn terms) asymptotically as both n,p→∞n,p\to\inftyn,p→∞ with log⁡p=o(n)\log p=o(n)logp=o(n).

View on arXiv
Comments on this paper