Trainability Enhancement of Parameterized Quantum Circuits via Reduced-Domain Parameter Initialization

Abstract

Parameterized quantum circuits (PQCs) have been widely used as a machine learning model to explore the potential of achieving quantum advantages for various tasks. However, the training of PQCs is notoriously challenging owing to the phenomenon of plateaus and/or the existence of (exponentially) many spurious local minima. In this work, we propose an efficient parameter initialization strategy with theoretical guarantees. We prove that if the initial domain of each parameter is reduced inversely proportional to the square root of circuit depth, then the magnitude of the cost gradient decays at most polynomially as a function of the depth. Our theoretical results are verified by numerical simulations of variational quantum eigensolver tasks. Moreover, we demonstrate that the reduced-domain initialization strategy can protect specific quantum neural networks from exponentially many spurious local minima. Our results highlight the significance of an appropriate parameter initialization strategy and can be used to enhance the trainability of PQCs in variational quantum algorithms.

Urban Regeneration and Residents’ Perception of Heritage Value in Haenggung-dong, Suwon, Korea

“…Indeed, finding good initial parameters is one of the most effective solutions to the vanishing gradient problem in classical neural networks [19,20]. Likewise, studies have shown that a quantum model can also have large initial gradients when parameters are initialized smartly [21][22][23][24][25][26][27][28]. However, most of the suggested initialization methods cannot be easily applied to large and deep circuits as they rely on heuristics developed from small circuits [22,23] or the proven lower bounds of gradient magnitudes are still too small for a deep circuit [25,26].…”