Learning Pure Quantum States in Any Dimension (Almost) Without Regret

2026-05-09

AI Summary

This work addresses the problem of efficiently learning an unknown pure quantum state in an arbitrary finite-dimensional Hilbert space with minimal cumulative disturbance. The proposed algorithm performs sequential rank-one projective measurements on fresh copies of the state, employing a phased strategy: at each phase, it conducts symmetric pairwise measurements along the negative direction of the tangent space of the current estimate on the pure-state manifold, uses the observed differences to linearly estimate the tangential error component, and refines the estimate via variance-adaptive robust estimation combined with warm-start regularization to propagate accuracy across phases. This approach overcomes the Bloch-sphere geometric constraints limited to qubits and extends low-disturbance pure-state tomography to high-dimensional qudit systems, revealing it as a universal geometric phenomenon on the pure-state manifold. The method achieves, for any d-dimensional pure state, a cumulative regret bound of 𝒪(d³ log²T) using T copies, and guarantees an online reconstruction error of 𝒪(d³ logT / t) at any time t ≤ T.

Abstract

We extend quantum state tomography with minimal cumulative disturbance, first investigated in [arXiv:2406.18370], to arbitrary finite-dimensional pure states. A learner sequentially receives fresh copies of an unknown pure state, chooses a rank-one projector for each copy using the previous outcomes, and performs the corresponding two-outcome projective measurement. The goal is to learn the state while keeping the chosen projectors close to the unknown state in order to minimize disturbance. The qubit solution relies on the special geometry of the Bloch sphere and does not extend directly to qudits, where pure states form a curved manifold. We show that this obstruction can be overcome by working locally on the pure-state manifold. The algorithm proceeds in epochs. In each epoch, it fixes a current estimate, measures pairs of nearby rank-one projectors obtained by moving in opposite tangent directions, and takes differences of the corresponding outcomes. This gives an exact linear observation of the tangent component of the error. The resulting local linear models are combined with a robust variance-adaptive estimator and a hot-start regularization that transfers precision across epochs. For every unknown pure state in dimension \(d\), after \(T\) measured copies, our protocol achieves cumulative regret \(\mathcal{O}(d^3\log^2 T)\), and at each intermediate time \(t\leq T\) its current estimate has online infidelity \(\mathcal{O}(d^3\log(T)/t)\). Hence, pure-state tomography with essentially no cumulative disturbance is not a peculiarity of qubits but a geometric phenomenon that persists for qudits.

Problem

• quantum state tomography
• pure states
• cumulative regret
• minimal disturbance
• qudits

Innovation

• quantum state tomography
• pure states
• cumulative regret
• manifold learning
• adaptive estimation