Algorithms for Approximating Conditionally Optimal Bounds

TL;DR

This paper introduces algorithms for constructing non-parametric confidence regions for discrete distributions, generalizing existing theories and providing approximation methods with diminishing error as mesh size decreases.

Contribution

It extends Learned-Miller's theory to preorders over sample spaces and develops several approximation algorithms with provable error bounds.

Findings

Closed form approximations with error tending to zero

Polynomial-time approximation scheme for quantile orders

Monte Carlo methods applicable to any mesh size

Abstract

This work develops algorithms for non-parametric confidence regions for samples from a univariate distribution whose support is a discrete mesh bounded on the left. We generalize the theory of Learned-Miller to preorders over the sample space. In this context, we show that the lexicographic low and lexicographic high orders are in some way extremal in the class of monotone preorders. From this theory we derive several approximation algorithms: 1) Closed form approximations for the lexicographic low and high orders with error tending to zero in the mesh size; 2) A polynomial-time approximation scheme for quantile orders with error tending to zero in the mesh size; 3) Monte Carlo methods for calculating quantile and lexicographic low orders applicable to any mesh size.