Natural gradient and parameter estimation for quantum Boltzmann machines

• URL: http://arxiv.org/abs/2410.24058v1
• Date: Thu, 31 Oct 2024 15:56:06 GMT
• Title: Natural gradient and parameter estimation for quantum Boltzmann machines
• Authors: Dhrumil Patel, Mark M. Wilde,
• Abstract summary: We establish formulas for the basic geometry of parameterized thermal states. We delineate quantum algorithms for estimating the values of these formulas. Results have applications in developing a natural gradient descent algorithm for quantum Boltzmann machine learning.
• Score: 3.9134031118910264
• License:
• 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 prove 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.

Related papers

• Quantum Boltzmann machine learning of ground-state energies [3.187381965457262]
  Esting the ground-state energy of Hamiltonians is a fundamental task for which quantum computers can be helpful. We analyze the performance of quantum Boltzmann machines for this task. Our algorithm estimates the gradient of the energy function efficiently by means of a novel quantum circuit construction.
  arXiv  Detail & Related papers  (2024-10-16T18:22:03Z)
• Quantum Simulation of Nonlinear Dynamical Systems Using Repeated Measurement [42.896772730859645]
  We present a quantum algorithm based on repeated measurement to solve initial-value problems for nonlinear ordinary differential equations. We apply this approach to the classic logistic and Lorenz systems in both integrable and chaotic regimes.
  arXiv  Detail & Related papers  (2024-10-04T18:06:12Z)
• Quantum Neural Estimation of Entropies [20.12693323453867]
  entropy measures quantify the amount of information and correlation present in a quantum system. We propose a variational quantum algorithm for estimating the von Neumann and R'enyi entropies, as well as the measured relative entropy and measured R'enyi relative entropy.
  arXiv  Detail & Related papers  (2023-07-03T17:30:09Z)
• Quantum data learning for quantum simulations in high-energy physics [55.41644538483948]
  We explore the applicability of quantum-data learning to practical problems in high-energy physics. We make use of ansatz based on quantum convolutional neural networks and numerically show that it is capable of recognizing quantum phases of ground states. The observation of non-trivial learning properties demonstrated in these benchmarks will motivate further exploration of the quantum-data learning architecture in high-energy physics.
  arXiv  Detail & Related papers  (2023-06-29T18:00:01Z)
• Neural network enhanced measurement efficiency for molecular groundstates [63.36515347329037]
  We adapt common neural network models to learn complex groundstate wavefunctions for several molecular qubit Hamiltonians. We find that using a neural network model provides a robust improvement over using single-copy measurement outcomes alone to reconstruct observables.
  arXiv  Detail & Related papers  (2022-06-30T17:45:05Z)
• Provably efficient variational generative modeling of quantum many-body systems via quantum-probabilistic information geometry [3.5097082077065003]
  We introduce a generalization of quantum natural gradient descent to parameterized mixed states. We also provide a robust first-order approximating algorithm, Quantum-Probabilistic Mirror Descent. Our approaches extend previously sample-efficient techniques to allow for flexibility in model choice.
  arXiv  Detail & Related papers  (2022-06-09T17:58:15Z)
• Probing finite-temperature observables in quantum simulators of spin systems with short-time dynamics [62.997667081978825]
  We show how finite-temperature observables can be obtained with an algorithm motivated from the Jarzynski equality. We show that a finite temperature phase transition in the long-range transverse field Ising model can be characterized in trapped ion quantum simulators.
  arXiv  Detail & Related papers  (2022-06-03T18:00:02Z)
• Numerical Simulations of Noisy Quantum Circuits for Computational Chemistry [51.827942608832025]
  Near-term quantum computers can calculate the ground-state properties of small molecules. We show how the structure of the computational ansatz as well as the errors induced by device noise affect the calculation.
  arXiv  Detail & Related papers  (2021-12-31T16:33:10Z)
• State preparation and measurement in a quantum simulation of the O(3) sigma model [65.01359242860215]
  We show that fixed points of the non-linear O(3) sigma model can be reproduced near a quantum phase transition of a spin model with just two qubits per lattice site. We apply Trotter methods to obtain results for the complexity of adiabatic ground state preparation in both the weak-coupling and quantum-critical regimes. We present and analyze a quantum algorithm based on non-unitary randomized simulation methods.
  arXiv  Detail & Related papers  (2020-06-28T23:44:12Z)
• Measuring Analytic Gradients of General Quantum Evolution with the Stochastic Parameter Shift Rule [0.0]
  We study the problem of estimating the gradient of the function to be optimized directly from quantum measurements. We derive a mathematically exact formula that provides an algorithm for estimating the gradient of any multi-qubit parametric quantum evolution. Our algorithm continues to work, although with some approximations, even when all the available quantum gates are noisy.
  arXiv  Detail & Related papers  (2020-05-20T18:24:11Z)
• Quantum Algorithms for Estimating Physical Quantities using Block-Encodings [0.30458514384586405]
  We present quantum algorithms for the estimation of n-time correlation functions, the local and non-local density of states, and dynamical linear response functions. All algorithms are based on block-encodings - a technique for the manipulation of arbitrary non-unitary combinations on a quantum computer.
  arXiv  Detail & Related papers  (2020-04-14T23:15:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.