1–6 Jun 2025
Taipei International Convention Center (TICC)
Asia/Taipei timezone

High efficiency multi-objective Bayesian algorithm for APS-U nonlinear dynamics tuning

THPM102
5 Jun 2025, 15:30
2h
Exhibiton Hall A _Magpie (TWTC)

Exhibiton Hall A _Magpie

TWTC

Poster Presentation MC6.D13 Machine Learning Thursday Poster Session

Speaker

Nikita Kuklev (Argonne National Laboratory)

Description

The Advanced Photon Source (APS) facility has just completed an upgrade to become one of the world’s brightest storage-ring light sources. Machine learning (ML) methods have seen extensive use during commissioning. One important application was multi-objective tuning of dynamic aperture and lifetime, a complex high-dimensionality task intractable with classic optimization methods. In this work we will discuss novel Bayesian optimization (BO) algorithmic and implementation improvements that enabled this use case. Namely, pre-training and uncertainty-aware simulation priors, dynamic parameter space and acquisition function refinement, and an adaptive wall-time convergence criteria. We will also show results of optimization runs from 10 to 24 dimensions, benchmarking scaling and efficiency as compared to standard MOGA and MGGPO. Given the promising performance, work is proceeding on tighter BO integration into the control room.

Funding Agency

The work is supported by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, under Contract No. DE-AC02-06CH11357.

Region represented America
Paper preparation format LaTeX

Author

Nikita Kuklev (Argonne National Laboratory)

Co-authors

Hairong Shang (Argonne National Laboratory) Louis Emery (Argonne National Laboratory) Michael Borland (Argonne National Laboratory) Yine Sun (Argonne National Laboratory)

Presentation materials

There are no materials yet.