# Patched-DeltaNet: Token-Level Event-Driven Memory for Linear-Time Anomaly Detection

arXiv: https://arxiv.org/abs/2605.27992 · HTML: https://mlsanity.com/paper/2605.27992/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 7 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 4 of 4)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting](https://mlsanity.com/paper/2602.17634/) (2026)

## Abstract (arXiv)

Time series anomaly detection is critical for maintaining the reliability of mission-critical systems. While Transformer-based models like PatchTST have shown remarkable performance, their O(L2) computational complexity severely limits deployment in resource-constrained environments. In this paper, we propose Patched-DeltaNet, a novel architecture combining time-series patching with Gated Delta Networks. By integrating these paradigms, we hypothesize and demonstrate the emergence of token-level event-driven memory, whereby the patching mechanism extracts local semantic chunks, while the error-driven DeltaNet updates its recurrent state exclusively when significant physical changes, defined as deltas, occur. This synergy effectively filters out background noise and captures sudden anomalous drifts. Our rigorous experiments on the Server Machine Dataset (SMD) benchmark demonstrate the structural superiority and sample efficiency of Patched-DeltaNet. By strictly outperforming recent architectures under unified evaluation constraints and identical compute budgets, our model yields an ROC-AUC of 0.957 and PA-F1 of 0.822, while drastically reducing computational complexity to the theoretical minimum of O(L/P).