Information geometry of nonmonotonic quantum natural gradient

Abstract

Natural gradient is an advanced optimization method based on information geometry, where the Fisher metric plays a crucial role. Its quantum counterpart, known as quantum natural gradient (QNG), employs the symmetric logarithmic derivative (SLD) metric, one of the quantum Fisher metrics. While quantization in physics is typically well-defined via the canonical commutation relations, the quantization of information-theoretic quantities introduces inherent arbitrariness. To resolve this ambiguity, monotonicity has been used as a guiding principle for constructing geometries in physics, as it aligns with physical intuition. Recently, a variant of QNG, which we refer to as nonmonotonic QNG in this paper, was proposed by relaxing the monotonicity condition. It was shown to achieve faster convergence compared to conventional QNG. In this paper, we investigate the properties of nonmonotonic QNG. To ensure the paper is self-contained, we first demonstrate that the SLD metric is locally optimal under the monotonicity condition and that non-monotone quantum Fisher metrics can lead to faster convergence in QNG. Previous studies primarily relied on a specific type of quantum divergence and assumed that density operators are full-rank. Here, we explicitly consider an alternative quantum divergence and extend the analysis to non-full-rank cases. Additionally, we explore how geometries can be designed using Petz functions, given that quantum Fisher metrics are characterized through them. Finally, we present numerical simulations comparing different quantum Fisher metrics in the context of parameter estimation problems in quantum circuit learning.

35 pages, 21 figures, accepted for publication in Quantum Machine Intelligence

References in corpus (37)

• Quantum Circuit Learning
• Rényi Divergence and Kullback-Leibler Divergence
• Circuit-centric quantum classifiers
• Quantum Fisher information matrix and multiparameter estimation
• 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
• Stochastic thermodynamics of chemical reaction networks
• Introduction to quantum Fisher information
• Variational Monte Carlo Method Combined with Quantum-Number Projection and Multi-Variable Optimization
• Quantum Fisher information for density matrices with arbitrary ranks
• Ideal Projective Measurements Have Infinite Resource Costs
• Discontinuities of the quantum Fisher information and the Bures metric
• Bures metric over thermal state manifolds and quantum criticality
• Green Function Monte Carlo with Stochastic Reconfiguration: an effective remedy for the sign problem disease
• Simple expression for the quantum Fisher information matrix
• Landauer vs. Nernst: What is the True Cost of Cooling a Quantum System?
• Fidelity susceptibility and quantum Fisher information for density operators with arbitrary ranks
• Quantum Fisher information and symmetric logarithmic derivative via anti-commutators
• Quantum natural gradient generalised to noisy and non-unitary circuits
• Time-dependent many-variable variational Monte Carlo method for nonequilibrium strongly correlated electron systems
• Geometric thermodynamics for the Fokker-Planck equation: Stochastic thermodynamic links between information geometry and optimal transport
• Finite temperature electronic simulations beyond the Born-Oppenheimer approximation
• Information Geometric Inequalities of Chemical Thermodynamics
• Determining the Continuous Family of Quantum Fisher Information from Linear Response Theory
• From Classical to Quantum Information Geometry: A Guide for Physicists
• $m^{\ast }$ of two-dimensional electron gas: a neural canonical transformation study
• Quantum measurements constrained by the third law of thermodynamics
• A Quantum Extension of Variational Bayes Inference
• Deterministic Quantum Annealing Expectation-Maximization Algorithm
• Information geometry of sandwiched Rényi $\alpha$-divergence
• Quantum Advantage in Variational Bayes Inference
• Quantum natural gradient without monotonicity
• Information geometric bound on general chemical reaction networks