Adaptive confidence intervals for regression functions under shape constraints

TL;DR

This paper develops adaptive confidence intervals for regression functions with shape constraints like monotonicity and convexity, achieving near-optimal expected length while maintaining coverage, and introduces a benchmark based on local modulus of continuity.

Contribution

It introduces a new benchmark for the expected length of confidence intervals under shape constraints and constructs intervals that adaptively achieve near-minimal length for individual functions.

Findings

Intervals have near-minimum expected length for each function.

Intervals maintain coverage probability within the shape-constrained class.

Benchmark based on local modulus of continuity guides optimality.

Abstract

Adaptive confidence intervals for regression functions are constructed under shape constraints of monotonicity and convexity. A natural benchmark is established for the minimum expected length of confidence intervals at a given function in terms of an analytic quantity, the local modulus of continuity. This bound depends not only on the function but also the assumed function class. These benchmarks show that the constructed confidence intervals have near minimum expected length for each individual function, while maintaining a given coverage probability for functions within the class. Such adaptivity is much stronger than adaptive minimaxity over a collection of large parameter spaces.