Combining Maximum-Likelihood with Deep Learning for Event Reconstruction in IceCube

TL;DR

This paper introduces a hybrid method combining deep learning and maximum-likelihood techniques to improve event reconstruction in IceCube, effectively leveraging domain knowledge and neural networks to address computational challenges.

Contribution

A novel hybrid approach using generative neural networks to approximate likelihoods, enabling domain knowledge integration in particle physics event reconstruction.

Findings

Effective approximation of likelihoods with neural networks

Enhanced event reconstruction accuracy in IceCube

Incorporation of domain invariances into deep learning models

Abstract

The field of deep learning has become increasingly important for particle physics experiments, yielding a multitude of advances, predominantly in event classification and reconstruction tasks. Many of these applications have been adopted from other domains. However, data in the field of physics are unique in the context of machine learning, insofar as their generation process and the laws and symmetries they abide by are usually well understood. Most commonly used deep learning architectures fail at utilizing this available information. In contrast, more traditional likelihood-based methods are capable of exploiting domain knowledge, but they are often limited by computational complexity. In this contribution, a hybrid approach is presented that utilizes generative neural networks to approximate the likelihood, which may then be used in a traditional maximum-likelihood setting. Domain knowledge, such as invariances and detector characteristics, can easily be incorporated in this approach. The hybrid approach is illustrated by the example of event reconstruction in IceCube.