Quantum Optimization for Training Quantum Neural Networks

TL;DR

This paper introduces a quantum optimization framework for training quantum neural networks, encoding cost functions into quantum states and using adaptive Hamiltonian tuning to potentially surpass classical methods and address barren plateau challenges.

Contribution

The paper proposes a novel quantum optimization approach that leverages quantum superposition and adaptive Hamiltonians to improve QNN training efficiency and mitigate barren plateau issues.

Findings

Framework encodes cost functions into quantum phases

Uses adaptive Hamiltonians for parameter tuning

Expected to outperform classical optimization methods

Abstract

Training quantum neural networks (QNNs) using gradient-based or gradient-free classical optimisation approaches is severely impacted by the presence of barren plateaus in the cost landscapes. In this paper, we devise a framework for leveraging quantum optimisation algorithms to find optimal parameters of QNNs for certain tasks. To achieve this, we coherently encode the cost function of QNNs onto relative phases of a superposition state in the Hilbert space of the network parameters. The parameters are tuned with an iterative quantum optimisation structure using adaptively selected Hamiltonians. The quantum mechanism of this framework exploits hidden structure in the QNN optimisation problem and hence is expected to provide beyond-Grover speed up, mitigating the barren plateau issue.