Incorporating Physical Priors into Weakly-Supervised Anomaly Detection

TL;DR

This paper introduces PAWS, a novel weakly-supervised anomaly detection method that leverages physical priors to significantly improve sensitivity, especially in noisy or rare signal scenarios, matching fully supervised methods without detailed parameter tuning.

Contribution

PAWS incorporates physical priors into weakly-supervised learning, enhancing anomaly detection sensitivity and robustness against irrelevant features, outperforming previous approaches.

Findings

PAWS extends detection sensitivity by a factor of 10 over previous methods.

PAWS remains insensitive to noise, unlike classical methods.

PAWS matches fully supervised sensitivity without needing exact signal parameters.

Abstract

We propose a new machine-learning-based anomaly detection strategy for comparing data with a background-only reference (a form of weak supervision). The sensitivity of previous strategies degrades significantly when the signal is too rare or there are many unhelpful features. Our Prior-Assisted Weak Supervision (PAWS) method incorporates information from a class of signal models to significantly enhance the search sensitivity of weakly supervised approaches. As long as the true signal is in the pre-specified class, PAWS matches the sensitivity of a dedicated, fully supervised method without specifying the exact parameters ahead of time. On the benchmark LHC Olympics anomaly detection dataset, our mix of semi-supervised and weakly supervised learning is able to extend the sensitivity over previous methods by a factor of 10 in cross section. Furthermore, if we add irrelevant (noise) dimensions to the inputs, classical methods degrade by another factor of 10 in cross section while PAWS remains insensitive to noise. This new approach could be applied in a number of scenarios and pushes the frontier of sensitivity between completely model-agnostic approaches and fully model-specific searches.