The complexity of quantum support vector machines

10Citations
Citations of this article
33Readers
Mendeley users who have this article in their library.

Abstract

Quantum support vector machines employ quantum circuits to define the kernel function. It has been shown that this approach offers a provable exponential speedup compared to any known classical algorithm for certain data sets. The training of such models corresponds to solving a convex optimization problem either via its primal or dual formulation. Due to the probabilistic nature of quantum mechanics, the training algorithms are affected by statistical uncertainty, which has a major impact on their complexity. We show that the dual problem can be solved in O(M4.67/ε2) quantum circuit evaluations, where M denotes the size of the data set and ε the solution accuracy compared to the ideal result from exact expectation values, which is only obtainable in theory. We prove under an empirically motivated assumption that the kernelized primal problem can alternatively be solved in O(min{M2/ε6, 1/ε10}) evaluations by employing a generalization of a known classical algorithm called Pegasos. Accompanying empirical results demonstrate these analytical complexities to be essentially tight. In addition, we investigate a variational approximation to quantum support vector machines and show that their heuristic training achieves considerably better scaling in our experiments.

Cite

CITATION STYLE

APA

Gentinetta, G., Thomsen, A., Sutter, D., & Woerner, S. (2024). The complexity of quantum support vector machines. Quantum, 8. https://doi.org/10.22331/q-2024-01-11-1225

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free