Computing the gradients with respect to all parameters of a quantum neural network using a single circuit
This addresses a bottleneck in training quantum neural networks, offering practical speedups for quantum machine learning applications.
The paper tackles the computational overhead of gradient calculation in quantum neural networks by proposing a method to compute all gradients using a single circuit, reducing circuit depth and classical registers. Experimental validation on simulators and IBM hardware shows significant reductions in circuit compilation time and total runtime.
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.