Continuous-variable quantum Gaussian process regression and quantum singular value decomposition of non-sparse low rank matrices
arXiv:1707.00360 · doi:10.1103/PhysRevA.97.022315
Abstract
With the significant advancement in quantum computation in the past couple of decades, the exploration of machine-learning subroutines using quantum strategies has become increasingly popular. Gaussian process regression is a widely used technique in supervised classical machine learning. Here we introduce an algorithm for Gaussian process regression using continuous-variable quantum systems that can be realized with technology based on photonic quantum computers under certain assumptions regarding distribution of data and availability of efficient quantum access. Our algorithm shows that by using a continuous-variable quantum computer a dramatic speed-up in computing Gaussian process regression can be achieved, i.e., the possibility of exponentially reducing the time to compute. Furthermore, our results also include a continuous-variable quantum-assisted singular value decomposition method of non-sparse low rank matrices and forms an important subroutine in our Gaussian process regression algorithm.
arXiv commentExpanded discussions surrounding SVD method and error analysis (Section IV A); to appear in PR A
References in corpus (12)
- Quantum Machine Learning
- Gaussian Quantum Information
- Quantum algorithm for solving linear systems of equations
- Quantum computation over continuous variables
- Quantum algorithms: an overview
- Quantum random access memory
- Quantum algorithm for systems of linear equations with exponentially improved dependence on precision
- Architectures for a quantum random access memory
- Quantum singular value decomposition of non-sparse low-rank matrices
- Quantum machine learning over infinite dimensions
- Quantum assisted Gaussian process regression
- Repeat-until-success cubic phase gate for universal continuous-variable quantum computation
Cited by in corpus (11)
- Continuous-variable quantum neural networks
- Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
- Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
- Quantum Singular Value Decomposer
- Quantum Imaginary Time Evolution Algorithm for Quantum Field Theories with Continuous Variables
- Entanglement and secret-key-agreement capacities of bipartite quantum interactions and read-only memory devices
- Protocol for implementing quantum nonparametric learning with trapped ions
- Non-parametric Bayesian approach to extrapolation problems in configuration interaction methods
- Quantum Machine Learning Algorithm for Knowledge Graphs
- Standing Wave Decomposition Gaussian Process
- Noisy dynamics of Gaussian entanglement: a transient bound entangled phase before separability