Quantum coupon collector with mixed-state encoding

TL;DR

This paper introduces a quantum coupon collector method using mixed-state encoding, significantly reducing sample complexity and simplifying state preparation, thus advancing quantum learning techniques.

Contribution

It proposes a novel mixed-state encoding for quantum coupon collection that is easier to prepare and achieves lower sample complexity than pure-state methods.

Findings

Reduces sample complexity from O(n) to O(log n) for single missing element

Uses Bell measurements on two copies for efficient set learning

No entanglement required in the mixed-state encoding

Abstract

The coupon collector is a prototypical model for evaluating the number of samples for identifying a set. By superposing all elements in the set as a pure quantum state, a quantum version of the coupon collector aims to learn the state, which is shown to reduce the sample complexity. Here we propose a quantum coupon collector by encoding the set into a mixed state, where the information of missing elements are labelled with Pauli strings. Remarkably, the encoded mixed state has no quantum entangled state and is easy to prepare. With such mixed-state encoding, it can be efficient to learn the set by performing Bell measurements on two copies and then extracting the missing element by solving a series of equations obtained from the measurements. Our protocol further reduces the sample complexity from $O(n)$ in the case of pure-state encoding to $O(\log n)$ when the missing element is one, where $n$ is the number of elements in the set. The mixed-state encoding scheme provides a new avenue for quantum learning and enlarges the realm for exploring quantum advantages.