Natural gradient and parameter estimation for quantum Boltzmann machines

Abstract

Thermal states play a fundamental role in various areas of physics, and they are becoming increasingly important in quantum information science, with applications related to semi-definite programming, quantum Boltzmann machine learning, Hamiltonian learning, and the related task of estimating the parameters of a Hamiltonian. Here we establish formulas underlying the basic geometry of parameterized thermal states, and we delineate quantum algorithms for estimating the values of these formulas. More specifically, we establish formulas for the Fisher--Bures and Kubo--Mori information matrices of parameterized thermal states, and our quantum algorithms for estimating their matrix elements involve a combination of classical sampling, Hamiltonian simulation, and the Hadamard test. These results have applications in developing a natural gradient descent algorithm for quantum Boltzmann machine learning, which takes into account the geometry of thermal states, and in establishing fundamental limitations on the ability to estimate the parameters of a Hamiltonian, when given access to thermal-state samples. For the latter task, and for the special case of estimating a single parameter, we sketch an algorithm that realizes a measurement that is asymptotically optimal for the estimation task. We finally stress that the natural gradient descent algorithm developed here can be used for any machine learning problem that employs the quantum Boltzmann machine ansatz.

arXiv commentv2: 24 pages, 4 figures, final version accepted for publication in Physical Review A

References in corpus (30)

• Barren plateaus in quantum neural network training landscapes
• Quantum Algorithms Revisited
• Hamiltonian Simulation by Qubitization
• Quantum Fisher information matrix and multiparameter estimation
• Connecting ansatz expressibility to gradient magnitudes and barren plateaus
• Toward the first quantum simulation with quantum speedup
• Quantum singular value transformation and beyond: exponential improvements for quantum matrix arithmetics
• Quantum Natural Gradient
• Quantum Boltzmann Machine
• A Geometric Perspective on Quantum Parameter Estimation
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• Equivalence of quantum barren plateaus to cost concentration and narrow gorges
• A Lie Algebraic Theory of Barren Plateaus for Deep Parameterized Quantum Circuits
• Sample-efficient learning of quantum many-body systems
• Fisher Information in Noisy Intermediate-Scale Quantum Applications
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
• Quantum Belief Propagation
• Quantum SDP-Solvers: Better upper and lower bounds
• The Adjoint Is All You Need: Characterizing Barren Plateaus in Quantum Ansätze
• Geometric distinguishability measures limit quantum channel estimation and discrimination
• Perturbative analysis of topological entanglement entropy from conditional independence
• Stability of topologically invariant order parameters at finite temperature
• Quantum many-body systems in thermal equilibrium
• On the Sample Complexity of Quantum Boltzmann Machine Learning
• Fundamental limits of metrology at thermal equilibrium
• Estimation of Hamiltonian parameters from thermal states
• Geometric approach to quantum statistical inference
• Quantum metrology in the finite-sample regime
• Quantum computational advantage with constant-temperature Gibbs sampling
• Rényi free energy and variational approximations to thermal states