Sequence-Model-Guided Measurement Selection for Quantum State Learning

TL;DR

This paper introduces a neural network-based method for adaptively selecting measurements in quantum state learning, improving efficiency and revealing boundary-bulk relationships in topological systems.

Contribution

A novel deep neural network with sequence modeling for data-driven measurement selection in quantum state characterization tasks.

Findings

Outperforms random measurement choices across multiple quantum tasks

Discovers boundary-related measurement strategies in topological systems

Enhances quantum state prediction and tomography efficiency

Abstract

Characterization of quantum systems from experimental data is a central problem in quantum science and technology. But which measurements should be used to gather data in the first place? While optimal measurement choices can be worked out for small quantum systems, the optimization becomes intractable as the system size grows large. To address this problem, we introduce a deep neural network with a sequence model architecture that searches for efficient measurement choices in a data-driven, adaptive manner. The model can be applied to a variety of tasks, including the prediction of linear and nonlinear properties of quantum states, as well as state clustering and state tomography tasks. In all these tasks, we find that the measurement choices identified by our neural network consistently outperform the uniformly random choice. Intriguingly, for topological quantum systems, our model tends to recommend measurements at the system's boundaries, even when the task is to predict bulk properties. This behavior suggests that the neural network may have independently discovered a connection between boundaries and bulk, without having been provided any built-in knowledge of quantum physics.