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

arXiv:2312.06152v2 Announce Type: replace-cross
Abstract: 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 …

abstract advantages arxiv cs.lg data experimental hep-ph learn meta meta-learning network neural network performance practical signal supervision train training transfer type via