Quantum natural gradient without monotonicity

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Sasaki, Toi, Miyahara, Hideyuki
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910579077152768
author Sasaki, Toi
Miyahara, Hideyuki
author_facet Sasaki, Toi
Miyahara, Hideyuki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_13237
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quantum natural gradient without monotonicity
Sasaki, Toi
Miyahara, Hideyuki
Quantum Physics
Statistical Mechanics
Information Theory
Computational Physics
Machine Learning
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.
title Quantum natural gradient without monotonicity
topic Quantum Physics
Statistical Mechanics
Information Theory
Computational Physics
Machine Learning
url https://arxiv.org/abs/2401.13237