RAMSeS: Robust and Adaptive Model Selection for Time-Series Anomaly Detection Algorithms
Not on the map. Why?
Abstract (arXiv)
Time-series data vary widely across domains, making a universal anomaly detector impractical. Methods that perform well on one dataset often fail to transfer because what counts as an anomaly is context dependent. The key challenge is to design a method that performs well in specific contexts while remaining adaptable across domains with varying data complexities. We present the Robust and Adaptive Model Selection for Time-Series Anomaly Detection RAMSeS framework. RAMSeS comprises two branches: (i) a stacking ensemble optimized with a genetic algorithm to leverage complementary detectors. (ii) An adaptive model-selection branch identifies the best single detector using techniques including Thompson sampling, robustness testing with generative adversarial networks, and Monte Carlo simulations. This dual strategy exploits the collective strength of multiple models and adapts to dataset-specific characteristics. We evaluate RAMSeS and show that it outperforms prior methods on F1.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 30 of its 102 references that are in the map. First posted on arXiv 25 Feb 2026.
Builds on
30 of 102 references.
References · 30
- 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,043
- 2024Chronos: Learning the Language of Time Seriescited by 737
- 2023A decoder-only foundation model for time-series forecastingcited by 674
- 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 623
- 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 468
- 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 408
- 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 390
- 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
- 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
- 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
- 2023FITS: Modeling Time Series with 10k Parameterscited by 190
- 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 149
18 more
- 2017Dilated Recurrent Neural Networkscited by 83
- 2020An Evaluation of Change Point Detection Algorithmscited by 63
- 2025TAB: Unified Benchmarking of Time Series Anomaly Detection Methodscited by 60
- 2021Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Versioncited by 35
- 2021A Survey on Anomaly Detection for Technical Systems using LSTM Networkscited by 27
- 2022Unsupervised Model Selection for Time-series Anomaly Detectioncited by 24
- 2018META-DES: A Dynamic Ensemble Selection Framework using Meta-Learningcited by 21
- 2019Shapley Values of Reconstruction Errors of PCA for Explaining Anomaly Detectioncited by 19
- 2022Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detectioncited by 16
- 2020Generic Outlier Detection in Multi-Armed Banditcited by 14
- 2020Automated Model Selection for Time-Series Anomaly Detectioncited by 9
- 2023Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classificationcited by 6
- 2022Time Series Anomaly Detection via Reinforcement Learning-Based Model Selectioncited by 4
- 2022An Anomaly Detection Method for Satellites Using Monte Carlo Dropoutcited by 4
- 2021Time Series Anomaly Detection with label-free Model Selectioncited by 3
- 2021Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approachcited by 3
- 2014EnsembleSVM: A Library for Ensemble Learning Using Support Vector Machinescited by 2
- 2024Meta-forests: Domain generalization on random forests with meta-learningcited by 2
Built on by
Not cited yet.