skip to main content

Title: Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge
Authors:
; ; ; ;
Award ID(s):
1955404 1747778 1703883
Publication Date:
NSF-PAR ID:
10223005
Journal Name:
Computer Vision and Pattern Recognition
Page Range or eLocation-ID:
6527 to 6536
Sponsoring Org:
National Science Foundation
More Like this
  1. A bstract Discoveries of new phenomena often involve a dedicated search for a hypothetical physics signature. Recently, novel deep learning techniques have emerged for anomaly detection in the absence of a signal prior. However, by ignoring signal priors, the sensitivity of these approaches is significantly reduced. We present a new strategy dubbed Quasi Anomalous Knowledge (QUAK), whereby we introduce alternative signal priors that capture some of the salient features of new physics signatures, allowing for the recovery of sensitivity even when the alternative signal is incorrect. This approach can be applied to a broad range of physics models and neural network architectures. In this paper, we apply QUAK to anomaly detection of new physics events at the CERN Large Hadron Collider utilizing variational autoencoders with normalizing flow.