English

A constrained risk inequality for general losses

Statistics Theory 2020-04-17 v3 Statistics Theory

Abstract

We provide a general constrained risk inequality that applies to arbitrary non-decreasing losses, extending a result of Brown and Low [Ann. Stat. 1996]. Given two distributions P0P_0 and P1P_1, we find a lower bound for the risk of estimating a parameter θ(P1)\theta(P_1) under P1P_1 given an upper bound on the risk of estimating the parameter θ(P0)\theta(P_0) under P0P_0. The inequality is a useful pedagogical tool, as its proof relies only on the Cauchy-Schwartz inequality, it applies to general losses, and it transparently gives risk lower bounds on super-efficient and adaptive estimators.

Keywords

Cite

@article{arxiv.1804.08116,
  title  = {A constrained risk inequality for general losses},
  author = {John C. Duchi and Feng Ruan},
  journal= {arXiv preprint arXiv:1804.08116},
  year   = {2020}
}

Comments

10 pages. This version (v2) adds applications to efficient nonparametric estimation and some pedagogical comments

R2 v1 2026-06-23T01:31:37.564Z