Quantum Recurrent Embedding Neural Network

TL;DR

This paper introduces a quantum recurrent embedding neural network (QRENN) that overcomes trainability issues in quantum neural networks, enabling scalable quantum supervised learning for complex physical problems.

Contribution

The paper proposes a novel QRENN architecture with proven trainability that resists classical simulation, advancing quantum neural network design and application.

Findings

QRENN avoids barren plateaus and trainability issues.

QRENN can classify quantum Hamiltonians accurately.

QRENN resists classical simulation, enabling scalable quantum learning.

Abstract

Quantum neural networks have emerged as promising quantum machine learning models, leveraging the properties of quantum systems and classical optimization to solve complex problems in physics and beyond. However, previous studies have demonstrated inevitable trainability issues that severely limit their capabilities in the large-scale regime. In this work, we propose a quantum recurrent embedding neural network (QRENN) inspired by fast-track information pathways in ResNet and general quantum circuit architectures in quantum information theory. By employing dynamical Lie algebras, we provide a rigorous proof of the trainability of QRENN circuits, demonstrating that this deep quantum neural network can avoid barren plateaus. Notably, the general QRENN architecture resists classical simulation as it encompasses powerful quantum circuits such as QSP, QSVT, and DQC1, which are widely believed to be classically intractable. Building on this theoretical foundation, we apply our QRENN to accurately classify quantum Hamiltonians and detect symmetry-protected topological phases, demonstrating its applicability in quantum supervised learning. Our results highlight the power of recurrent data embedding in quantum neural networks and the potential for scalable quantum supervised learning in predicting physical properties and solving complex problems.