Quantum natural gradient without monotonicity

TL;DR

This paper introduces a generalized quantum natural gradient method that removes the traditional monotonicity constraint, demonstrating improved convergence speed over conventional methods in quantum optimization tasks.

Contribution

It proposes a non-monotone quantum natural gradient approach and provides analytical and numerical evidence of its superior performance.

Findings

Non-monotone QNG outperforms conventional QNG in convergence speed.

Monotonicity is essential for the optimality of traditional QNG.

Analytical and numerical results support the advantages of the generalized approach.

Abstract

Natural gradient (NG) is an information-geometric optimization method that plays a crucial role, especially in the estimation of parameters for machine learning models like neural networks. To apply NG to quantum systems, the quantum natural gradient (QNG) was introduced and utilized for noisy intermediate-scale devices. Additionally, a mathematically equivalent approach to QNG, known as the stochastic reconfiguration method, has been implemented to enhance the performance of quantum Monte Carlo methods. It is worth noting that these methods are based on the symmetric logarithmic derivative (SLD) metric, which is one of the monotone metrics. So far, monotonicity has been believed to be a guiding principle to construct a geometry in physics. In this paper, we propose generalized QNG by removing the condition of monotonicity. Initially, we demonstrate that monotonicity is a crucial condition for conventional QNG to be optimal. Subsequently, we provide analytical and numerical evidence showing that non-monotone QNG outperforms conventional QNG based on the SLD metric in terms of convergence speed.