mlsanityData to 14 Oct 2026

Resonant Anomaly Detection with Multiple Reference Datasets

arXiv 2212.10579 ↗First posted 20 Dec 2022hep-ph cs.LG hep-excited by 4

Not on the map. Why?

Abstract (arXiv)

An important class of techniques for resonant anomaly detection in high energy physics builds models that can distinguish between reference and target datasets, where only the latter has appreciable signal. Such techniques, including Classification Without Labels (CWoLa) and Simulation Assisted Likelihood-free Anomaly Detection (SALAD) rely on a single reference dataset. They cannot take advantage of commonly-available multiple datasets and thus cannot fully exploit available information. In this work, we propose generalizations of CWoLa and SALAD for settings where multiple reference datasets are available, building on weak supervision techniques. We demonstrate improved performance in a number of settings with realistic and synthetic data. As an added benefit, our generalizations enable us to provide finite-sample guarantees, improving on existing asymptotic analyses.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 17 of its 51 references that are in the map. First posted on arXiv 20 Dec 2022.

Builds on

17 of 51 references.

References · 17

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Snorkel: Rapid Training Data Creation with Weak Supervisioncited by 372
  3. 2016Data Programming: Creating Large Training Sets, Quicklycited by 246
  4. 2018Training Complex Models with Multi-Task Weak Supervisioncited by 106
  5. 2020Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methodscited by 98
  6. 2015Approximating Likelihood Ratios with Calibrated Discriminative Classifierscited by 90
  7. 2021A Living Review of Machine Learning for Particle Physicscited by 78
  8. 2020Anomaly Detection with Density Estimationcited by 72
  9. 2021Machine Learning in the Search for New Fundamental Physicscited by 50
  10. 2017Classification without labels: Learning from mixed samples in high energy physicscited by 43
  11. 2019Learning Dependency Structures for Weak Supervision Modelscited by 32
  12. 2021The Dark Machines Anomaly Score Challenge: Benchmark Data and Model Independent Event Classification for the Large Hadron Collidercited by 29
5 more
  1. 2020Simulation Assisted Likelihood-free Anomaly Detectioncited by 27
  2. 2022Learning new physics efficiently with nonparametric methodscited by 21
  3. 2021E Pluribus Unum Ex Machina: Learning from Many Collider Events at Oncecited by 15
  4. 2020Simulation-Assisted Decorrelation for Resonant Anomaly Detectioncited by 13
  5. 2021New Methods and Datasets for Group Anomaly Detection From Fundamental Physicscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 1; 2026: 1.

4 papers.

  1. 2023Anomalies, Representations, and Self-Supervisioncited by 11
  2. 2023CURTAINs Flows For Flows: Constructing Unobserved Regions with Maximum Likelihood Estimationcited by 10
  3. 2026Model-Agnostic Signal Discovery with Machine Learning: Bridging the Gap Between Theory and Practicecited by 3
  4. 2025Weak Supervision for Real World Graphscited by 0