Learning Broken Symmetries with Resimulation and Encouraged Invariance

Understand

Recognizing symmetries in data allows for significant boosts in neural network training.

• In many cases, however, the underlying symmetry is present only in an idealized dataset, and is broken in the training data, due to effects such as arbitrary and/or non-uniform detector bin edges.
• Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the full, broken symmetry.
• We introduce a novel data-augmentation scheme that respects the true underlying symmetry and avoids artifacts by augmenting the training set with transformed pre-detector examples whose detector response is then resimulated.