Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization
arXiv:2610.02345v1 Announce Type: new Abstract: A family of tabular anomaly detectors trains a neural map toward a fixed target under squared-error loss and scores anomalies by the test-time residual; contraction matching, one-step rectified flow, and reconstruction autoencoders all fit this templa…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-05 04:00 · arXiv cs.LG
Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization