Variational Dropout Sparsification for Particle Identification speed-up
This work addresses the need for faster PID in LHC upgrade conditions, which is incremental as it applies known speed-up techniques to a specific domain.
The paper tackled the problem of speeding up particle identification (PID) for the LHCb experiment by applying neural network speed-up techniques, achieving a prediction speed increase of up to a factor of sixteen using variational dropout sparsification.
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.