RangeAD: Fast On-Model Anomaly Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917351682736128 |
|---|---|
| author | Hinkamp, Luca Klüttermann, Simon Müller, Emmanuel |
| author_facet | Hinkamp, Luca Klüttermann, Simon Müller, Emmanuel |
| contents | In practice, machine learning methods commonly require anomaly detection (AD) to filter inputs or detect distributional shifts. Typically, this is implemented by running a separate AD model alongside the primary model. However, this separation ignores the fact that the primary model already encodes substantial information about the target distribution. In this paper, we introduce On-Model AD, a setting for anomaly detection that explicitly leverages access to a related machine learning model. Within this setting, we propose RangeAD, an algorithm that utilizes neuron-wise output ranges derived from the primary model. RangeAD achieves superior performance even on high-dimensional tasks while incurring substantially lower inference costs. Our results demonstrate the potential of the On-Model AD setting as a practical framework for efficient anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17795 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RangeAD: Fast On-Model Anomaly Detection Hinkamp, Luca Klüttermann, Simon Müller, Emmanuel Machine Learning Artificial Intelligence In practice, machine learning methods commonly require anomaly detection (AD) to filter inputs or detect distributional shifts. Typically, this is implemented by running a separate AD model alongside the primary model. However, this separation ignores the fact that the primary model already encodes substantial information about the target distribution. In this paper, we introduce On-Model AD, a setting for anomaly detection that explicitly leverages access to a related machine learning model. Within this setting, we propose RangeAD, an algorithm that utilizes neuron-wise output ranges derived from the primary model. RangeAD achieves superior performance even on high-dimensional tasks while incurring substantially lower inference costs. Our results demonstrate the potential of the On-Model AD setting as a practical framework for efficient anomaly detection. |
| title | RangeAD: Fast On-Model Anomaly Detection |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2603.17795 |