Reproduce “Low-Rank and Structured Sparse Tensor Decomposition for Anomaly Detection in Multivariate Functional Data” 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
Mohammad N. Bisheh, Che-Yi Liao, Kamran Paynabar
FG-Lasso detects anomalies in correlated manufacturing sensor profiles by decomposing sample-sensor-time data into recurring low-rank CP structure and sparse departures. It combines entrywise sparsity with group selection over each sample-sensor time fiber, while ES-CP uses entrywise sparsity alone. In filtered forging data, FG-Lasso reaches macro F1 0.85 versus 0.82, but has lower faulty-class recall than ES-CP; results are not held-out.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.