.png){kind=icon}
.png){kind=icon}
Return
Quantum Algorithms for Escaping from Saddle Points
.png){kind=icon}
OA
AI
DOI：10.22331/q-2021-08-20-529.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We initiate the study of quantum algorithms for escaping from saddle points with provable guarantee. Given a function f : R-n -> R, our quantum algorithm outputs an epsilon-approximate second-order stationary point using (O) over tilde (log(2) (n)/epsilon(1.75))(1) queries to the quantum evaluation oracle (i.e., the zeroth-order oracle). Compared to the classical state-of-the-art algorithm by Jin et al. with (O) over tilde (log(6) (n)/epsilon(1.75)) queries to the gradient oracle (i.e., the first-order oracle), our quantum algorithm is polynomially better in terms of log n and matches its complexity in terms of 1/epsilon. Technically, our main contribution is the idea of replacing the classical perturbations in gradient descent methods by simulating quantum wave equations, which constitutes the improvement in the quantum query complexity with log n factors for escaping from saddle points. We also show how to use a quantum gradient computation algorithm due to Jordan to replace the classical gradient queries by quantum evaluation queries with the same complexity. Finally, we also perform numerical experiments that support our theoretical findings.
Keywords:
LINEAR SCHRODINGER-EQUATIONS
SOBOLEV NORMS
SIMULATION
SYSTEMS
GROWTH
SPEED
Journal
IF:
5.4
Papers:
951
Citations:
1.0W