On Suboptimality of Least Squares with Application to Estimation of Convex Bodies

06/07/2020
by   Gil Kur, et al.
0

We develop a technique for establishing lower bounds on the sample complexity of Least Squares (or, Empirical Risk Minimization) for large classes of functions. As an application, we settle an open problem regarding optimality of Least Squares in estimating a convex set from noisy support function measurements in dimension d≥ 6. Specifically, we establish that Least Squares is mimimax sub-optimal, and achieves a rate of Θ̃_d(n^-2/(d-1)) whereas the minimax rate is Θ_d(n^-4/(d+3)).

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/06/2022

Efficient Minimax Optimal Estimators For Multivariate Convex Regression

We study the computational aspects of the task of multivariate convex re...
research
09/07/2016

Chaining Bounds for Empirical Risk Minimization

This paper extends the standard chaining technique to prove excess risk ...
research
12/30/2022

On Undersmoothing and Sample Splitting for Estimating a Doubly Robust Functional

We consider the problem of constructing minimax rate-optimal estimators ...
research
04/14/2021

Enumerating All Convex Polyhedra Glued from Squares in Polynomial Time

We present an algorithm that enumerates and classifies all edge-to-edge ...
research
06/16/2020

Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions

Empirical Risk Minimization (ERM) algorithms are widely used in a variet...
research
02/07/2021

Lower Bounds and Accelerated Algorithms for Bilevel Optimization

Bilevel optimization has recently attracted growing interests due to its...
research
06/28/2023

Theory and applications of the Sum-Of-Squares technique

The Sum-of-Squares (SOS) approximation method is a technique used in opt...

Please sign up or login with your details

Forgot password? Click here to reset