Research

Paper

TESTING March 12, 2026

Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows

Authors

David Baumgartner, Eliezer de Souza da Silva, Iñigo Urteaga

Abstract

Deep generative models for anomaly detection in multivariate time-series are typically trained by maximizing data likelihood. However, likelihood in observation space measures marginal density rather than conformity to structured temporal dynamics, and therefore can assign high probability to anomalous or out-of-distribution samples. We address this structural limitation by relocating the notion of anomaly to a prescribed latent space. We introduce explicit inductive biases in conditional normalizing flows, modeling time-series observations within a discrete-time state-space framework that constrains latent representations to evolve according to prescribed temporal dynamics. Under this formulation, expected behavior corresponds to compliance with a specified distribution over latent trajectories, while anomalies are defined as violations of these dynamics. Anomaly detection is consequently reduced to a statistically grounded compliance test, such that observations are mapped to latent space and evaluated via goodness-of-fit tests against the prescribed latent evolution. This yields a principled decision rule that remains effective even in regions of high observation likelihood. Experiments on synthetic and real-world time-series demonstrate reliable detection of anomalies in frequency, amplitude, and observation noise, while providing interpretable diagnostics of model compliance.

Metadata

arXiv ID: 2603.11756
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-12
Fetched: 2026-03-13 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11756v1</id>\n    <title>Anomaly detection in time-series via inductive biases in the latent space of conditional normalizing flows</title>\n    <updated>2026-03-12T10:02:38Z</updated>\n    <link href='https://arxiv.org/abs/2603.11756v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11756v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Deep generative models for anomaly detection in multivariate time-series are typically trained by maximizing data likelihood. However, likelihood in observation space measures marginal density rather than conformity to structured temporal dynamics, and therefore can assign high probability to anomalous or out-of-distribution samples. We address this structural limitation by relocating the notion of anomaly to a prescribed latent space. We introduce explicit inductive biases in conditional normalizing flows, modeling time-series observations within a discrete-time state-space framework that constrains latent representations to evolve according to prescribed temporal dynamics. Under this formulation, expected behavior corresponds to compliance with a specified distribution over latent trajectories, while anomalies are defined as violations of these dynamics. Anomaly detection is consequently reduced to a statistically grounded compliance test, such that observations are mapped to latent space and evaluated via goodness-of-fit tests against the prescribed latent evolution. This yields a principled decision rule that remains effective even in regions of high observation likelihood. Experiments on synthetic and real-world time-series demonstrate reliable detection of anomalies in frequency, amplitude, and observation noise, while providing interpretable diagnostics of model compliance.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-12T10:02:38Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>David Baumgartner</name>\n    </author>\n    <author>\n      <name>Eliezer de Souza da Silva</name>\n    </author>\n    <author>\n      <name>Iñigo Urteaga</name>\n    </author>\n  </entry>"
}