Protocol for implementing quantum nonparametric learning with trapped ions

Abstract

Nonparametric learning is able to make reliable predictions by extracting information from similarities between a new set of input data and all samples. Here we point out a quantum paradigm of nonparametric learning which offers an exponential speedup over the sample size. By encoding data into quantum feature space, similarity between the data is defined as an inner product of quantum states. A quantum training state is introduced to superpose all data of samples, encoding relevant information for learning in its bipartite entanglement spectrum. We demonstrate that a trained state for prediction can be obtained by entanglement spectrum transformation, using quantum matrix toolbox. We further work out a feasible protocol to implement the quantum nonparametric learning with trapped ions, and demonstrate the power of quantum superposition for machine learning.

5 pages. Close to published version

References in corpus (13)

• Quantum algorithm for solving linear systems of equations
• Quantum computing with trapped ions
• Quantum Data Fitting
• Benchmarking an 11-qubit quantum computer
• Quantum-enhanced machine learning
• Architectures for a quantum random access memory
• Dirac Equation and Quantum Relativistic Effects in a Single Trapped Ion
• Quantum harmonic oscillator state synthesis by reservoir engineering
• Trapped ion quantum computation with transverse phonon modes
• Quantum amplification of mechanical oscillator motion
• Machine learning meets quantum physics
• Continuous-Variable Instantaneous Quantum Computing is hard to sample
• A proposal for a scalable universal bosonic simulator using individually trapped ions

Cited by in corpus (13)

• Towards understanding the power of quantum kernels in the NISQ era
• Quantum Differentially Private Sparse Regression Learning
• Selected topics of quantum computing for nuclear physics
• Continuous-variable assisted thermal quantum simulation
• Experimental realization of a quantum image classifier via tensor-network-based machine learning
• Quantum-enhanced least-square support vector machine: simplified quantum algorithm and sparse solutions
• Quantum Gaussian filter for exploring ground-state properties
• Quantum kernels with squeezed-state encoding for machine learning
• Ancilla-Error-Transparent Controlled Beam Splitter Gate
• Inverse iteration quantum eigensolvers assisted with a continuous variable
• Adaptive random compiler for Hamiltonian simulation
• Variational quantum simulation of the quantum critical regime
• Fluctuation-guided adaptive random compiler for Hamiltonian simulation