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. 1902.00648
11
0

Fast Approximation and Estimation Bounds of Kernel Quadrature for Infinitely Wide Models

2 February 2019
Sho Sonoda
ArXivPDFHTML
Abstract

An infinitely wide model is a weighted integration ∫φ(x,v)dμ(v)\int \varphi(x,v) d \mu(v)∫φ(x,v)dμ(v) of feature maps. This model excels at handling an infinite number of features, and thus it has been adopted to the theoretical study of deep learning. Kernel quadrature is a kernel-based numerical integration scheme developed for fast approximation of expectations ∫f(x)dp(x)\int f(x) d p(x)∫f(x)dp(x). In this study, regarding the weight μ\muμ as a signed (or complex/vector-valued) distribution of parameters, we develop the general kernel quadrature (GKQ) for parameter distributions. The proposed method can achieve a fast approximation rate O(e−p)O(e^{-p})O(e−p) with parameter number ppp, which is faster than the traditional Barron's rate, and a fast estimation rate O~(1/n)\widetilde{O}(1/n)O(1/n) with sample size nnn. As a result, we have obtained a new norm-based complexity measure for infinitely wide models. Since the GKQ implicitly conducts the empirical risk minimization, we can understand that the complexity measure also reflects the generalization performance in the gradient learning setup.

View on arXiv
Comments on this paper