On the Generalization Properties of Selective State-Space Models for Filtering Tasks for Unknown Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908994327543808 |
|---|---|
| author | Tang, Alex Ildiz, M. Emrullah Kurt, Batin Oymak, Samet Ozay, Necmiye |
| author_facet | Tang, Alex Ildiz, M. Emrullah Kurt, Batin Oymak, Samet Ozay, Necmiye |
| contents | Selective State-Space Models (SSMs) such as Mamba have emerged as an alternative architecture to self-attention based transformers in sequence modeling tasks. Recent works have demonstrated the use of transformers in some filtering and output prediction tasks via in-context learning. In this paper, we analyze whether structured SSMs can work equally well for filtering of unknown systems. In particular, we train the SSM on trajectory samples from a set of systems. At run-time, the SSM is given the outputs of an unknown system from the same set and is expected to predict the next output online. Theoretically, under appropriate assumptions, we derive generalization bounds as to why SSMs succeed in such tasks. Empirically, we demonstrate the performance via several numerical examples. We also discuss the advantages and disadvantages of SSMs versus transformers for this task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_23818 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | On the Generalization Properties of Selective State-Space Models for Filtering Tasks for Unknown Systems Tang, Alex Ildiz, M. Emrullah Kurt, Batin Oymak, Samet Ozay, Necmiye Systems and Control Selective State-Space Models (SSMs) such as Mamba have emerged as an alternative architecture to self-attention based transformers in sequence modeling tasks. Recent works have demonstrated the use of transformers in some filtering and output prediction tasks via in-context learning. In this paper, we analyze whether structured SSMs can work equally well for filtering of unknown systems. In particular, we train the SSM on trajectory samples from a set of systems. At run-time, the SSM is given the outputs of an unknown system from the same set and is expected to predict the next output online. Theoretically, under appropriate assumptions, we derive generalization bounds as to why SSMs succeed in such tasks. Empirically, we demonstrate the performance via several numerical examples. We also discuss the advantages and disadvantages of SSMs versus transformers for this task. |
| title | On the Generalization Properties of Selective State-Space Models for Filtering Tasks for Unknown Systems |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2604.23818 |