view article
Figure 10
The eight-dimensional optimization of the simulated TES beamline, where the degrees of freedom comprise the toroidal and Kirkpatrick–Baez mirrors. The colors show different varieties of Bayesian optimization algorithms both with and without latent inputs and composite outputs, with both the cumulative maximum of all individual runs (thin lines) and the median cumulative maximum (thick line). Each variety starts out with a quasi-random sampling of 32 points (shaded light blue) and then performs a Bayesian optimization loop with the expected improvement acquisition function. The benefit of using both latent inputs and composite outputs is shown, as we can achieve a better optimum more robustly and more quickly.

Journal logoJOURNAL OF
SYNCHROTRON
RADIATION
ISSN: 1600-5775
Volume 31| Part 6| November 2024| Pages 1446-1456
https://doi.org/10.1107/S1600577524008993
Follow J. Synchrotron Rad.
Sign up for e-alerts
E-alerts
Follow J. Synchrotron Rad. on Twitter
Twitter
Follow us on facebook
Facebook
Sign up for RSS feeds
RSS