Quantum Bootstrap Aggregation
We set out a strategy for quantizing attribute bootstrap aggregation to enable variance-resilient quantum machine learning. To do so, we utilise the linear decomposability of decision boundary parameters in the Rebentrost et al. Support Vector Machine to guarantee that stochastic measurement of the output quantum state will give rise to an ensemble decision without destroying the superposition over projective feature subsets induced within the chosen SVM implementation. We achieve a linear performance advantage, O(d), in addition to the existing O(log(n)) advantages of quantization as applied to Support Vector Machines. The approach extends to any form of quantum learning giving rise to linear decision boundaries.
KeywordsSupport Vector Machine Training Vector Quantum Superposition Query Oracle Random Subspace Method
The first author would like to acknowledge financial support from the Horizon 2020 European Research project DREAMS4CARS (#731593). The second author is partially supported by EU ICT COST Action IC1405 “Reversible Computation—Extending Horizons of Computing”.
- 1.Rebentrost, P., Mohseni, M., Lloyd, S.: Quantum support vector machine for big data classification. Phys. Rev. Lett. 113 (2014). 130501Google Scholar
- 3.Altaisky, M., Zolnikova, N., Kaputkina, N., Krylov, V., Lozovik, Y.E., Dattani, N.S.: Towards a feasible implementation of quantum neural networks using quantum dots, arXiv preprint arXiv:1503.05125
- 7.Tucci, R.R.: Quantum circuit for discovering from data the structure of classical bayesian networks, arXiv preprint arXiv:1404.0055
- 8.Wiebe, N., Kapoor, A., Svore, K.: Quantum algorithms for nearest-neighbor methods for supervised and unsupervised learning, arXiv preprint arXiv:1401.2142
- 12.Valentini, G., Dietterich, T.G.: Low bias bagged support vector machines. In: International Conference on Machine Learning, ICML-2003, pp. 752–759. Morgan Kaufmann (2003)Google Scholar