Computing the gradients with respect to all parameters of a quantum neural network using a single circuit

TL;DR

This paper introduces a method to compute all gradients of a quantum neural network with a single quantum circuit, greatly reducing computational overhead and circuit depth compared to traditional methods.

Contribution

The authors propose a novel approach to calculate all parameter gradients in quantum neural networks using only one circuit, improving efficiency over the parameter-shift rule.

Findings

Reduces circuit compilation time significantly

Demonstrates speedup on quantum simulators and hardware

Maintains accuracy of gradient computation

Abstract

Finding gradients is a crucial step in training machine learning models. For quantum neural networks, computing gradients using the parameter-shift rule requires calculating the cost function twice for each adjustable parameter in the network. When the total number of parameters is large, the quantum circuit must be repeatedly adjusted and executed, leading to significant computational overhead. Here we propose an approach to compute all gradients using a single circuit only, significantly reducing both the circuit depth and the number of classical registers required. We experimentally validate our approach on both quantum simulators and IBM's real quantum hardware, demonstrating that our method significantly reduces circuit compilation time compared to the conventional approach, resulting in a substantial speedup in total runtime.