English

Variational Dropout Sparsification for Particle Identification speed-up

Data Analysis, Statistics and Probability 2020-08-26 v1 Machine Learning

Abstract

Accurate particle identification (PID) is one of the most important aspects of the LHCb experiment. Modern machine learning techniques such as neural networks (NNs) are efficiently applied to this problem and are integrated into the LHCb software. In this research, we discuss novel applications of neural network speed-up techniques to achieve faster PID in LHC upgrade conditions. We show that the best results are obtained using variational dropout sparsification, which provides a prediction (feedforward pass) speed increase of up to a factor of sixteen even when compared to a model with shallow networks.

Keywords

Cite

@article{arxiv.2001.07493,
  title  = {Variational Dropout Sparsification for Particle Identification speed-up},
  author = {Artem Ryzhikov and Denis Derkach and Mikhail Hushchyn},
  journal= {arXiv preprint arXiv:2001.07493},
  year   = {2020}
}
R2 v1 2026-06-23T13:16:27.444Z