Help us make Indico better by taking this survey! Aidez-nous à améliorer Indico en répondant à ce sondage !

10–12 Oct 2022
National Centre of Physical and Technological Sciences
Europe/Vilnius timezone

Evolutionary algorithms for hyperparameter optimization in machine learning for application in high energy physics

Not scheduled
20m
A101 (National Centre of Physical and Technological Sciences)

A101

National Centre of Physical and Technological Sciences

National Centre of Physical and Technological Sciences Saulėtekio al. 3, Vilnius LT-10257, Lithuania

Speaker

Laurits Tani (National Institute of Chemical Physics and Biophysics (EE))

Description

In contemporary high energy physics (HEP) experiments the analysis of vast amounts of data represents a major challenge. In order to overcome this challenge various machine learning (ML) methods are employed. However, in addition to the choice of the ML algorithm a multitude of algorithm-specific parameters, referred to as hyperparameters, need to be specified in practical applications of ML methods. The optimization of these hyperparameters, which is often performed manually, has a significant impact on the performance of the ML algorithm. In this talk we explore several evolutionary algorithms that allow to determine optimal hyperparameters for a given ML task in a fully automated way. Additionally, we study the capability of the two most promising hyperparameter optimisation algorithms, particle swarm optimization and bayesian optimization, for utilising the highly parallel computing architecture that is typical for the field of HEP.

Primary authors

Christian Veelken (National Institute of Chemical Physics and Biophysics (EE)) Laurits Tani (National Institute of Chemical Physics and Biophysics (EE))

Co-authors

Diana Rand (National Institute of Chemical Physics and Biophysics (EE)) Mario Kadastik (National Institute of Chemical Physics and Biophysics (EE))

Presentation materials

There are no materials yet.