Metraipolis › archive › dc_8f7ffbcb5082
FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction — arXiv:2608.15727
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15727
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:04:20.578Z
- SHA-256 of the archived text
6bb8193f24999d16de541460b8ff9223eefa0abb2f0e9196ee736179615227cf- Stable URL of this page
https://metraipolis.com/documento/dc_8f7ffbcb5082
How to cite
FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction — arXiv:2608.15727 — arXiv (en), https://arxiv.org/abs/2608.15727 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8f7ffbcb5082 (Metraipolis archive dc_8f7ffbcb5082, sha256 6bb8193f24999d16de541460b8ff9223eefa0abb2f0e9196ee736179615227cf)
BibTeX
@misc{dc8f7ffbcb5082,
title = {FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction — arXiv:2608.15727},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15727},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8f7ffbcb5082; sha256 6bb8193f24999d16de541460b8ff9223eefa0abb2f0e9196ee736179615227cf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15727. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion models have recently shown strong potential for multivariate time-series anomaly detection by learning the distribution of normal data through iterative denoising. Existing diffusion-based approaches, however, typically perform anomaly detection after completing the reverse diffusion process, relying primarily on the final reconstructed signal and overlooking informative representations produced during denoising. This design incurs substantial computational cost and limits the use of intermediate diffusion information for anomaly detection. In this paper, we propose FirstDiff, a diffusion-based anomaly detection framework based on the observation that the predicted diffusion noise at the initial reverse-diffusion evaluation already contains sufficient information for accurate anomaly detection. FirstDiff models the statistical distribution of predicted diffusion noise under normal behavior using validation data, enabling anomaly inference from a single denoising-network evaluation rather than completing the reverse diffusion trajectory. To model complex temporal and inter-sensor dependencies, FirstDiff employs a Diffusion Transformer as the denoising backbone. Extensive experiments on five public benchmark datasets demonstrate that FirstDiff achieves state-of-the-art performance while reducing diffusion inference from the full reverse trajectory to a single denoising-network evaluation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2608.15727 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:14.045Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).