Improving the performance of weak supervision searches using transfer and meta-learning

A bstract Weak supervision searches have in principle the advantages of both being able to train on experimental data and being able to learn distinctive signal properties. However, the practical applicability of such searches is limited by the fact that successfully training a neural network via we...

Full description

Saved in:

Bibliographic Details
Published in:	The journal of high energy physics 2024-02, Vol.2024 (2), p.138-19
Main Authors:	Beauchesne, Hugues, Chen, Zong-En, Chiang, Cheng-Wei
Format:	Article
Language:	eng
Subjects:	Classical and Quantum Gravitation Deep learning Elementary Particles Learning Neural networks New Gauge Interactions Performance enhancement Physics Physics and Astronomy Quantum Field Theories Quantum Field Theory Quantum Physics Regular Article - Theoretical Physics Relativity Theory Searching Simulation Specific BSM Phenomenology String Theory Supervision Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	A bstract Weak supervision searches have in principle the advantages of both being able to train on experimental data and being able to learn distinctive signal properties. However, the practical applicability of such searches is limited by the fact that successfully training a neural network via weak supervision can require a large amount of signal. In this work, we seek to create neural networks that can learn from less experimental signal by using transfer and meta-learning. The general idea is to first train a neural network on simulations, thereby learning concepts that can be reused or becoming a more efficient learner. The neural network would then be trained on experimental data and should require less signal because of its previous training. We find that transfer and meta-learning can substantially improve the performance of weak supervision searches.
ISSN:	1029-8479