Quantum algorithm for finding the negative curvature direction

Kaining Zhang, Min-Hsiu Hsieh, Liu Liu, Dacheng Tao

TL;DR: We present an efficient quantum algorithm aiming to find the negative curvature direction.

Abstract: We present an efficient quantum algorithm aiming to find the negative curvature direction for escaping the saddle point, which is a critical subroutine for many second-order non-convex optimization algorithms. We prove that our algorithm could produce the target state corresponding to the negative curvature direction with query complexity O(polylog(d)ε^(-1)), where d is the dimension of the optimization function. The quantum negative curvature finding algorithm is exponentially faster than any known classical method which takes time at least O(dε^(−1/2)). Moreover, we propose an efficient algorithm to achieve the classical read-out of the target state. Our classical read-out algorithm runs exponentially faster on the degree of d than existing counterparts.

Keywords: quantum algorithm, negative curvature