Incorporating Physical Priors into Weakly Supervised Anomaly Detection
- Univ. of Wisconsin, Madison, WI (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); University of California, Berkeley, CA (United States); Stanford Univ., CA (United States); SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)
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 prespecified 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 semisupervised 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.
- Research Organization:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF); USDOE Office of Science (SC), Office of Workforce Development for Teachers & Scientists (WDTS)
- Grant/Contract Number:
- AC02-05CH11231; SC0017647
- OSTI ID:
- 2583310
- Journal Information:
- Physical Review Letters, Journal Name: Physical Review Letters Journal Issue: 2 Vol. 135; ISSN 1079-7114; ISSN 0031-9007
- Publisher:
- American Physical Society (APS)Copyright Statement
- Country of Publication:
- United States
- Language:
- English