Reproduce “A Meta-level Analysis of Online Anomaly Detectors” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Antonios Ntroumpogiannis, Michail Giannoulis, Nikolaos Myrtakis, Vassilis Christophides, Eric Simon, Ioannis Tsamardinos
The authors compare existing online and offline anomaly detectors for flagging unusual measurements as data arrive, using streaming updates and common evaluation metrics. Across 24 real datasets, online XSTREAM won by ROC AUC on 9 of 24, with a 3.6% average gap from dataset’s winner. However, nine of 16 variants were close to random on at least half of datasets.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.