Correcting Convexity Bias in Function and Functional Estimate

08/17/2022
by   Chao Ma, et al.
0

A general framework with a series of different methods is proposed to improve the estimate of convex function (or functional) values when only noisy observations of the true input are available. Technically, our methods catch the bias introduced by the convexity and remove this bias from a baseline estimate. Theoretical analysis are conducted to show that the proposed methods can strictly reduce the expected estimate error under mild conditions. When applied, the methods require no specific knowledge about the problem except the convexity and the evaluation of the function. Therefore, they can serve as off-the-shelf tools to obtain good estimate for a wide range of problems, including optimization problems with random objective functions or constraints, and functionals of probability distributions such as the entropy and the Wasserstein distance. Numerical experiments on a wide variety of problems show that our methods can significantly improve the quality of the estimate compared with the baseline method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/08/2021

How type of Convexity of the Core function affects the Csiszár f-divergence functional

We investigate how the type of Convexity of the Core function affects th...
research
11/21/2014

On the Impossibility of Convex Inference in Human Computation

Human computation or crowdsourcing involves joint inference of the groun...
research
03/21/2020

A level set representation method for N-dimensional convex shape and applications

In this work, we present a new efficient method for convex shape represe...
research
12/27/2021

Yet Another Proof of the Joint Convexity of Relative Entropy

The joint convexity of the map (X,A) ↦ X^* A^-1 X, an integral represent...
research
11/24/2021

Learning to Refit for Convex Learning Problems

Machine learning (ML) models need to be frequently retrained on changing...
research
07/31/2015

Fast Stochastic Algorithms for SVD and PCA: Convergence Properties and Convexity

We study the convergence properties of the VR-PCA algorithm introduced b...
research
05/11/2021

Frank-Wolfe Methods in Probability Space

We introduce a new class of Frank-Wolfe algorithms for minimizing differ...

Please sign up or login with your details

Forgot password? Click here to reset