Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2306.00582 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910437337989120 |
|---|---|
| author | Rozner, Amit Battash, Barak Li, Henry Wolf, Lior Lindenbaum, Ofir |
| author_facet | Rozner, Amit Battash, Barak Li, Henry Wolf, Lior Lindenbaum, Ofir |
| contents | We propose a modified density estimation problem that is highly effective for detecting anomalies in tabular data. Our approach assumes that the density function is relatively stable (with lower variance) around normal samples. We have verified this hypothesis empirically using a wide range of real-world data. Then, we present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples while minimizing the variance of the density around normal samples. To obtain a reliable anomaly detector, we introduce a spectral ensemble of autoregressive models for learning the variance-stabilized distribution. We have conducted an extensive benchmark with 52 datasets, demonstrating that our method leads to state-of-the-art results while alleviating the need for data-specific hyperparameter tuning. Finally, we have used an ablation study to demonstrate the importance of each of the proposed components, followed by a stability analysis evaluating the robustness of our model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_00582 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Anomaly Detection with Variance Stabilized Density Estimation Rozner, Amit Battash, Barak Li, Henry Wolf, Lior Lindenbaum, Ofir Machine Learning Artificial Intelligence I.2 We propose a modified density estimation problem that is highly effective for detecting anomalies in tabular data. Our approach assumes that the density function is relatively stable (with lower variance) around normal samples. We have verified this hypothesis empirically using a wide range of real-world data. Then, we present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples while minimizing the variance of the density around normal samples. To obtain a reliable anomaly detector, we introduce a spectral ensemble of autoregressive models for learning the variance-stabilized distribution. We have conducted an extensive benchmark with 52 datasets, demonstrating that our method leads to state-of-the-art results while alleviating the need for data-specific hyperparameter tuning. Finally, we have used an ablation study to demonstrate the importance of each of the proposed components, followed by a stability analysis evaluating the robustness of our model. |
| title | Anomaly Detection with Variance Stabilized Density Estimation |
| topic | Machine Learning Artificial Intelligence I.2 |
| url | https://arxiv.org/abs/2306.00582 |