2025/03/28 by Alberto Padoan, Padoan, Alberto, Jeremy Coulson +1 · 1 citation
Computer Science · #Time Series Analysis and Forecasting #Anomaly Detection Techniques and Applications #Data Stream Mining Techniques
paper · pdf · doi:10.48550/arxiv.2503.22849
The paper introduces a class of distances for linear behaviors over finite time horizons. These distances allow for comparisons between finite-horizon linear behaviors represented by matrices of possibly different dimensions. They remain invariant under coordinate changes, rotations, and permutations, ensuring independence from input-output partitions. Moreover, they naturally encode complexity-misfit trade-offs for Linear Time-Invariant (LTI) behaviors, providing a principled solution to a longstanding puzzle in behavioral systems theory. The resulting framework characterizes modeling as a minimum distance problem, identifying the Most Powerful Unfalsified Model (MPUM) as optimal among all systems unfalsified by a given dataset. Finally, we illustrate the value of these metrics in a time series anomaly detection task, where their finer resolution yields superior performance over existing distances.