On Quantum Speedups for Nonconvex Optimization via Quantum Tunneling Walks
This addresses the challenge of escaping local minima in nonconvex optimization for fields like machine learning, but it is incremental as it focuses on specific landscape conditions.
The paper tackles nonconvex optimization problems with high barriers between local minima by introducing a quantum tunneling walk (QTW) algorithm, showing it achieves quantum speedup over classical stochastic gradient descent in specific landscapes like double-well setups.
Classical algorithms are often not effective for solving nonconvex optimization problems where local minima are separated by high barriers. In this paper, we explore possible quantum speedups for nonconvex optimization by leveraging the global effect of quantum tunneling. Specifically, we introduce a quantum algorithm termed the quantum tunneling walk (QTW) and apply it to nonconvex problems where local minima are approximately global minima. We show that QTW achieves quantum speedup over classical stochastic gradient descents (SGD) when the barriers between different local minima are high but thin and the minima are flat. Based on this observation, we construct a specific double-well landscape, where classical algorithms cannot efficiently hit one target well knowing the other well but QTW can when given proper initial states near the known well. Finally, we corroborate our findings with numerical experiments.