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. 1312.4349
80
26

Empirical risk minimization is optimal for the convex aggregation problem

16 December 2013
Guillaume Lecué
ArXivPDFHTML
Abstract

Let FFF be a finite model of cardinality MMM and denote by conv⁡(F)\operatorname {conv}(F)conv(F) its convex hull. The problem of convex aggregation is to construct a procedure having a risk as close as possible to the minimal risk over conv⁡(F)\operatorname {conv}(F)conv(F). Consider the bounded regression model with respect to the squared risk denoted by R(⋅)R(\cdot)R(⋅). If f^nERM−C{\widehat{f}}_n^{\mathit{ERM-C}}f​nERM−C​ denotes the empirical risk minimization procedure over conv⁡(F)\operatorname {conv}(F)conv(F), then we prove that for any x>0x>0x>0, with probability greater than 1−4exp⁡(−x)1-4\exp(-x)1−4exp(−x), \[R({\widehat{f}}_n^{\mathit{ERM-C}})\leq\min_{f\in \operatorname {conv}(F)}R(f)+c_0\max \biggl(\psi_n^{(C)}(M),\frac{x}{n}\biggr),\] where c0>0c_0>0c0​>0 is an absolute constant and ψn(C)(M)\psi_n^{(C)}(M)ψn(C)​(M) is the optimal rate of convex aggregation defined in (In Computational Learning Theory and Kernel Machines (COLT-2003) (2003) 303-313 Springer) by ψn(C)(M)=M/n\psi_n^{(C)}(M)=M/nψn(C)​(M)=M/n when M≤nM\leq \sqrt{n}M≤n​ and ψn(C)(M)=log⁡(eM/n)/n\psi_n^{(C)}(M)=\sqrt{\log (\mathrm{e}M/\sqrt{n})/n}ψn(C)​(M)=log(eM/n​)/n​ when M>nM>\sqrt{n}M>n​.

View on arXiv
Comments on this paper