Uncertainty Quantification for Matrix Compressed Sensing and Quantum Tomography Problems

TL;DR

This paper develops minimax optimal confidence sets for low-rank matrix recovery, enabling adaptive measurement procedures with proven optimality, and applies these methods to quantum tomography with theoretical guarantees and simulations.

Contribution

It introduces non-asymptotic confidence sets for matrix recovery, leading to adaptive sampling strategies with optimal stopping times, specifically applied to quantum tomography.

Findings

Confidence sets are minimax optimal in Frobenius norm.

Adaptive sampling procedures guarantee true matrix recovery.

Simulation studies confirm theoretical properties.

Abstract

We construct minimax optimal non-asymptotic confidence sets for low rank matrix recovery algorithms such as the Matrix Lasso or Dantzig selector. These are employed to devise adaptive sequential sampling procedures that guarantee recovery of the true matrix in Frobenius norm after a data-driven stopping time $\hat n$ for the number of measurements that have to be taken. With high probability, this stopping time is minimax optimal. We detail applications to quantum tomography problems where measurements arise from Pauli observables. We also give a theoretical construction of a confidence set for the density matrix of a quantum state that has optimal diameter in nuclear norm. The non-asymptotic properties of our confidence sets are further investigated in a simulation study.