Fully Neural-Based Out-of-Distribution Detection for Temporal Point Processes
Keywords: Temporal Point Processes, Anomaly Detection, Deep Learning
TL;DR: Using deep learning for modeling temporal point processes' datasets so as to be able to distinguish anomalous sequences
Abstract: Temporal Point Processes have undergone increasing relevance in the modeling of continuous-time event streams. Regarding their applicability, one important aspect is that of detecting anomalous, or out-of-distribution, sequences. Recent works have focused on parametric models for this out-of-distribution detection. In the present work, we give a theoretical background treatment of the anomaly detection problem applied to TPPs, describe our fully neural-based strategy, show how a fully neural-based strategy of improved generalization outperforms traditional parametric approaches, and validate its effectiveness against a state-of-the-art approach on data of controlled generation.
Submission Number: 17
Loading