Review and experimental benchmarking of machine learning algorithms for efficient optimization of cold atom experiments
O. Anton1,5, V.A. Henderson1,5, E. Da Ros1, I. Sekulic2,3, S. Burger2,3, P.-I. Schneider2,3 and M. Krutzik1,4
Published in:
Mach. Learn.: Sci. Technol., vol. 5, no. 2, pp. 025022, doi:10.1088/2632-2153/ad3cb6 (2024).
Abstract:
The generation of cold atom clouds is a complex process which involves the optimization of noisy data in high dimensional parameter spaces. Optimization can be challenging both in and especially outside of the lab due to lack of time, expertise, or access for lengthy manual optimization. In recent years, it was demonstrated that machine learning offers a solution since it can optimize high dimensional problems quickly, without knowledge of the experiment itself. In this paper we present results showing the benchmarking of nine different optimization techniques and implementations, alongside their ability to optimize a rubidium (Rb) cold atom experiment. The investigations are performed on a 3D 87Rb molasses with 10 and 18 adjustable parameters, respectively, where the atom number obtained by absorption imaging was chosen as the test problem. We further compare the best performing optimizers under different effective noise conditions by reducing the signal-to-noise ratio of the images via adapting the atomic vapor pressure in the 2D+ magneto-optical trap and the detection laser frequency stability.
1 Institut für Physik and IRIS, Humboldt-Universität zu Berlin, Newtonstr. 15, 12489 Berlin, Germany
2 JCMwave GmbH, Bolivarallee 22, 14050 Berlin, Germany
3 Zuse Institute Berlin (ZIB), Takustraße 7, 14195 Berlin, Germany
4 Ferdinand-Braun-Institut (FBH), Gustav-Kirchhoff-Str. 4, 12489 Berlin, Germany
5 O.A. and V.A.H. are joint first authors
Keywords:
machine learning, cold atoms, optimization, Bayesian optimization, benchmarking, noisy expected improvement
© 2024 The Author(s). Published by IOP Publishing Ltd
Original Content from this work may be used under the terms of the Creative Commons Attribution 4.0 licence.
Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Full version in pdf-format.