Near-Optimal Recovery of Linear and N-Convex Functions on Unions of Convex Sets

TL;DR

This paper develops near-optimal, computationally feasible estimators for linear and N-convex functionals of signals within unions of convex sets, based on indirect noisy observations, with theoretical guarantees.

Contribution

It introduces a new approach to estimate N-convex functionals on unions of convex sets with provable near-optimality and computational efficiency.

Findings

Estimates are derived from explicit convex optimization problems.

Achieves near-minimax optimal risk bounds.

Applicable to Gaussian and similar observation schemes.

Abstract

In this paper we build provably near-optimal, in the minimax sense, estimates of linear forms and, more generally, "$N$-convex functionals" (the simplest example being the maximum of several fractional-linear functions) of unknown "signal" known to belong to the union of finitely many convex compact sets from indirect noisy observations of the signal. Our main assumption is that the observation scheme in question is good in the sense of A. Goldenshluger, A. Juditsky, A. Nemirovski, Electr. J. Stat. 9(2) (2015), arXiv:1311.6765, the simplest example being the Gaussian scheme where the observation is the sum of linear image of the signal and the standard Gaussian noise. The proposed estimates, same as upper bounds on their worst-case risks, stem from solutions to explicit convex optimization problems, making the estimates "computation-friendly."