Geometric SSM: LTI State Space Models for Selective Tasks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Casti, Umberto, Baggio, Giacomo, Zampieri, Sandro, Pasqualetti, Fabio
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914386544689152
author Casti, Umberto
Baggio, Giacomo
Zampieri, Sandro
Pasqualetti, Fabio
author_facet Casti, Umberto
Baggio, Giacomo
Zampieri, Sandro
Pasqualetti, Fabio
contents A key claim in recent work on Selective State Space Models is that selectivity, the ability to focus on relevant information while filtering irrelevant inputs, requires breaking the Linear Time-Invariant (LTI) property through time-varying dynamics. We challenge this claim by demonstrating that LTI systems can achieve selectivity when designed using principles from geometric control. We introduce the Geometric SSM, in which different input patterns excite distinct invariant subspaces of the dynamics. Unlike Mamba's memoryless selection mechanism, our approach employs a dynamic residual generator that maintains temporal memory, enabling recognition of multi-token patterns without time-varying system matrices. The Geometric SSM achieves near-perfect performance on a novel extended induction head task where Mamba fails, while preserving efficient FFT-based training. Our results demonstrate that geometric control theory can inform the design of novel selective sequence models that combine theoretical rigor with practical efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17932
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Geometric SSM: LTI State Space Models for Selective Tasks
Casti, Umberto
Baggio, Giacomo
Zampieri, Sandro
Pasqualetti, Fabio
Systems and Control
Machine Learning
A key claim in recent work on Selective State Space Models is that selectivity, the ability to focus on relevant information while filtering irrelevant inputs, requires breaking the Linear Time-Invariant (LTI) property through time-varying dynamics. We challenge this claim by demonstrating that LTI systems can achieve selectivity when designed using principles from geometric control. We introduce the Geometric SSM, in which different input patterns excite distinct invariant subspaces of the dynamics. Unlike Mamba's memoryless selection mechanism, our approach employs a dynamic residual generator that maintains temporal memory, enabling recognition of multi-token patterns without time-varying system matrices. The Geometric SSM achieves near-perfect performance on a novel extended induction head task where Mamba fails, while preserving efficient FFT-based training. Our results demonstrate that geometric control theory can inform the design of novel selective sequence models that combine theoretical rigor with practical efficiency.
title Geometric SSM: LTI State Space Models for Selective Tasks
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2505.17932