DOE OSTI · 2496653
Learning linear optical circuits with coherent states
Abstract
We analyze the energy and training data requirements for supervised learning of an M-mode linear optical circuit by minimizing an empirical risk defined solely from the action of the circuit on coherent states. When the linear optical circuit acts non-trivially only on k < M unknown modes (i.e. a linear optical k-junta), we provide an energy-efficient, adaptive algorithm that identifies the junta set and learns the circuit. We compare two schemes for allocating a total energy, E, to the learning algorithm. In the first scheme, each of the T random training coherent states has energy E/T. In the second scheme, a single random MT-mode coherent state with energy E is partitioned into T training coherent states. The latter scheme exhibits a polynomial advantage in training data size sufficient for convergence of the empirical risk to the full risk due to concentration of measure on the $(2MT-1)$-sphere. Specifically, generalization bounds for both schemes are proven, which indicate that for ε-approximation of the full risk by the empirical risk with high probability, $O(E^{2/3}M^{2/3}/\epsilon^{2/3})$ training states are sufficient for the first scheme and $O(E^{1/3}M^{1/3}/\epsilon^{2/3})$ training states are sufficient for the second scheme.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Volkoff, Tyler James, Sornborger, Andrew Tyler. 2024-07-12. Learning linear optical circuits with coherent states. https://doi.org/10.1088/1751-8121%2Fad5cac. https://searchnasa.com/record/osti%3A2496653/learning-linear-optical-circuits-with-coherent-states
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.