Geometry and symmetry in quantum Boltzmann machine

Abstract

Quantum Boltzmann machine extends the classical Boltzmann machine learning to the quantum regime, which makes its power to simulate the quantum states beyond the classical probability distributions. We develop the BFGS algorithm to study the corresponding optimization problem in quantum Boltzmann machine, especially focus on the target states being a family of states with parameters. As an typical example, we study the target states being the real symmetric two-qubit pure states, and we find two obvious features shown in the numerical results on the minimal quantum relative entropy: First, the minimal quantum relative entropy in the first and the third quadrants is zero; Second, the minimal quantum relative entropy is symmetric with the axes $y=x$ and $y=-x$ even with one qubit hidden layer. Then we theoretically prove these two features from the geometric viewpoint and the symmetry analysis. Our studies show that the traditional physical tools can be used to help us to understand some interesting results from quantum Boltzmann machine learning.

References in corpus (23)

• Quantum Machine Learning
• An introduction to quantum machine learning
• Quantum algorithms for supervised and unsupervised machine learning
• Quantum Boltzmann Machine
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Experimental signature of programmable quantum annealing
• Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
• Application of Quantum Annealing to Training of Deep Neural Networks
• Tomography and Generative Data Modeling via Quantum Boltzmann Training
• Constructing exact representations of quantum many-body systems with deep neural networks
• Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models
• Irreducible multi-particle correlations in states without maximal rank
• Maximum Quantum Entropy Method
• Computing complexity measures for quantum states based on exponential families
• Symmetry Breaking and the Geometry of Reduced Density Matrices
• Symmetry Breaking and Convex Set Phase Diagrams for the q-state Potts Model
• Discontinuity of Maximum Entropy Inference and Quantum Phase Transitions
• Irreducible multiparty correlation can be created by local operations
• A robust BFGS algorithm for unconstrained nonlinear optimization problems
• Physical origins of ruled surfaces on the reduced density matrices geometry
• Irreducible many-body correlations in topologically ordered systems
• BFGS convergence to nonsmooth minimizers of convex functions
• An efficient numerical algorithm on irreducible multiparty correlations

Cited by in corpus (2)

• Clustering of conditional mutual information for quantum Gibbs states above a threshold temperature
• Group theory on quantum Boltzmann machine