Quantum natural gradient without monotonicity

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.

arXiv comment6 pages, 3 figures

References in corpus (18)

• Quantum Computing in the NISQ era and beyond
• Quantum Circuit Learning
• Rényi Divergence and Kullback-Leibler Divergence
• Circuit-centric quantum classifiers
• On quantum Renyi entropies: a new generalization and some properties
• Tensor networks for complex quantum systems
• Strong converse for the classical capacity of entanglement-breaking and Hadamard channels via a sandwiched Renyi relative entropy
• Quantum Natural Gradient
• Generalized Lanczos Algorithm for Variational Quantum Monte Carlo
• Green Function Monte Carlo with Stochastic Reconfiguration: an effective remedy for the sign problem disease
• Quantum natural gradient generalised to noisy and non-unitary circuits
• Finite temperature electronic simulations beyond the Born-Oppenheimer approximation
• $m^{\ast }$ of two-dimensional electron gas: a neural canonical transformation study
• A Quantum Extension of Variational Bayes Inference
• Deterministic Quantum Annealing Expectation-Maximization Algorithm
• Ansatz-Independent Variational Quantum Classifier
• Information geometry of sandwiched Rényi $\alpha$-divergence
• Quantum Advantage in Variational Bayes Inference

Cited by in corpus (2)

• Second-order optimisation strategies for neural network quantum states
• Information geometry of nonmonotonic quantum natural gradient