Hybrid Quantum-Classical Scheduling for Accelerating Neural Network Training with Newton's Gradient Descent

arXiv:2405.00252v1 Announce Type: cross
Abstract: Optimization techniques in deep learning are predominantly led by first-order gradient methodologies, such as SGD. However, neural network training can greatly benefit from the rapid convergence characteristics of second-order optimization. Newton's GD stands out in this category, by rescaling the gradient using the inverse Hessian. Nevertheless, one of its major bottlenecks is matrix inversion, which is notably time-consuming in $O(N^3)$ time with weak scalability.
Matrix inversion can be translated into solving a series of linear …

abstract arxiv benefit convergence cs.ai cs.lg deep learning gradient however hybrid network network training neural network optimization quant-ph quantum scheduling training type