Deep Learning in High-Energy Physics: Improving the Search for Exotic Particles

Collisions at high-energy particle colliders are a traditionally fruitful source of exotic particle discoveries. Finding these rare exotic particles requires solving difficult signal-versus-background classification problems, hence machine learning approaches are often used for this task. Standard approaches in the past have relied on ‘shallow’ machine learning models that have a limited capacity to learn complex non-linear functions of the inputs, and rely on a pain-staking search through manually constructed non-linear inputs. Progress on this problem has slowed, as a variety of techniques (neural networks, boosted decision trees, support vector machines) have shown equivalent performance. Recent advances in the field of deep learning, particularly with artificial neural networks, make it possible to learn more complex functions and better discriminate between signal and background classes. Using benchmark datasets, we show that deep learning methods need no manually constructed inputs and yet improve the AUC (Area Under the ROC Curve) classification metric by as much as 8% over the best current approaches. This is a large relative improvement and demonstrates that deep learning approaches can improve the power of collider searches for exotic particles.