An analog quantum variational embedding classifier

Quantum machine learning could provide powerful algorithms for artificial intelligence. The pursuit of quantum advantage in quantum machine learning is an active area of research. For current noisy, intermediate-scale quantum (NISQ) computers, various quantum-classical hybrid algorithms have been proposed. One such hybrid algorithm is a gate-based variational embedding classifier, which is made up of a classical neural network and a parameterized gate-based quantum computer. We propose a quantum variational embedding classifier based on an analog quantum computer, where control signals vary continuously: our particular focus is implementation with quantum annealers. In our algorithm, the classical data is transformed into the parameters of the time-dependent Hamiltonian of the analog quantum computer by a linear transformation. The nonlinearity needed for a nonlinear classification task arises purely from the dynamics of the analog quantum computer, through the nonlinear dependence of the final quantum state on the control parameters of the Hamiltonian. We performed numerical simulations to demonstrate the effectiveness of our algorithm for performing binary and multi-class classification on datasets such as concentric circles and MNIST digits. We find that the performance of the classifier can be increased by increasing the number of qubits in the analog quantum computer. Our work has implications for using quantum annealers for solving practical machine-learning problems and is relevant for exploring quantum advantage in quantum machine learning.