Learning To Optimize Quantum Neural Network Without Gradients

TL;DR

This paper introduces a gradient-free meta-optimization algorithm for training quantum neural networks, reducing reliance on quantum gradient computations and improving efficiency and quality of solutions.

Contribution

It proposes a novel meta-optimizer network that trains quantum circuits without gradient information, outperforming traditional gradient-based methods.

Findings

Achieves better minima with fewer circuit evaluations.

Demonstrates effectiveness on multiple datasets.

Reduces impact of hardware noise in quantum training.

Abstract

Quantum Machine Learning is an emerging sub-field in machine learning where one of the goals is to perform pattern recognition tasks by encoding data into quantum states. This extension from classical to quantum domain has been made possible due to the development of hybrid quantum-classical algorithms that allow a parameterized quantum circuit to be optimized using gradient based algorithms that run on a classical computer. The similarities in training of these hybrid algorithms and classical neural networks has further led to the development of Quantum Neural Networks (QNNs). However, in the current training regime for QNNs, the gradients w.r.t objective function have to be computed on the quantum device. This computation is highly non-scalable and is affected by hardware and sampling noise present in the current generation of quantum hardware. In this paper, we propose a training algorithm that does not rely on gradient information. Specifically, we introduce a novel meta-optimization algorithm that trains a \emph{meta-optimizer} network to output parameters for the quantum circuit such that the objective function is minimized. We empirically and theoretically show that we achieve a better quality minima in fewer circuit evaluations than existing gradient based algorithms on different datasets.