A Permutation-equivariant Deep Learning Model for Quantum State Characterization

TL;DR

This paper introduces a permutation-equivariant deep learning model integrated with threshold quantum state tomography to efficiently characterize quantum states, reducing measurement complexity and demonstrating robustness up to 4 qubits.

Contribution

It presents a novel deep learning approach that combines permutation-equivariance with tQST, improving quantum state characterization efficiency.

Findings

Effective quantum state tomography up to 4 qubits.

Model robust to measurement noise.

Reduced measurement requirements compared to traditional methods.

Abstract

The characterization of quantum states is a fundamental step of any application of quantum technologies. Nowadays there exist several approaches addressing this problem, also based on machine and deep learning techniques. However, all these approaches usually require a number of measurement that scales exponentially with the number of parties composing the system. Threshold quantum state tomography (tQST) addresses this problem and, in some cases of interest, can significantly reduce the number of measurements. In this paper, we study how to combine a permutation-equivariant deep learning model with the tQST protocol. We test the model on quantum state tomography and purity estimation. Finally, we validate the robustness of the model to noise. We show results up to 4 qubits.