IPAC2021 - List of Authors (Ben Ghali, M.)

Paper	Title	Page
THPAB201	A Machine Learning Technique for Dynamic Aperture Computation	4172
	B. Dalena, M. Ben Ghali CEA-IRFU, Gif-sur-Yvette, France
	Currently, dynamic aperture calculations of high-energy hadron colliders are performed through computer simulations, which are both a resource-heavy and time-costly processes. The aim of this study is to use a reservoir computing machine learning model in order to achieve a faster extrapolation of dynamic aperture values. A recurrent echo-state network (ESN) architecture is used as a basis for this work. Recurrent networks are better fitted to extrapolation tasks while the reservoir echo-state structure is computationally effective. Model training and validation is conducted on a set of "seeds" corresponding to the simulation results of different machine configurations. Adjustments in the model architecture, manual metric and data selection, hyper-parameters tuning and the introduction of new parameters enabled the model to reliably achieve good performance on examining testing sets.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB201
About •	paper received ※ 14 May 2021 paper accepted ※ 22 July 2021 issue date ※ 02 September 2021
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

A Machine Learning Technique for Dynamic Aperture Computation

4172

B. Dalena, M. Ben Ghali
CEA-IRFU, Gif-sur-Yvette, France

Currently, dynamic aperture calculations of high-energy hadron colliders are performed through computer simulations, which are both a resource-heavy and time-costly processes. The aim of this study is to use a reservoir computing machine learning model in order to achieve a faster extrapolation of dynamic aperture values. A recurrent echo-state network (ESN) architecture is used as a basis for this work. Recurrent networks are better fitted to extrapolation tasks while the reservoir echo-state structure is computationally effective. Model training and validation is conducted on a set of "seeds" corresponding to the simulation results of different machine configurations. Adjustments in the model architecture, manual metric and data selection, hyper-parameters tuning and the introduction of new parameters enabled the model to reliably achieve good performance on examining testing sets.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB201

About •

paper received ※ 14 May 2021 paper accepted ※ 22 July 2021 issue date ※ 02 September 2021

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)