Metraipolis › archive › dc_f3086efcdba6

Riccati State Space Models: Non-iterative Parallelization for Nonlinear Sequence Modeling — arXiv:2609.35441

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35441
License (as archived)
CC0-1.0
Archived
2026-10-07T21:03:38.239Z
SHA-256 of the archived text
4cc466193b627d4cd9976d83ffccd7107da14f53dc946eaf9bb1e283ac787b64
Stable URL of this page
https://metraipolis.com/documento/dc_f3086efcdba6

How to cite

Riccati State Space Models: Non-iterative Parallelization for Nonlinear Sequence Modeling — arXiv:2609.35441 — arXiv (en), https://arxiv.org/abs/2609.35441 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3086efcdba6 (Metraipolis archive dc_f3086efcdba6, sha256 4cc466193b627d4cd9976d83ffccd7107da14f53dc946eaf9bb1e283ac787b64)
BibTeX
@misc{dcf3086efcdba6,
  title = {Riccati State Space Models: Non-iterative Parallelization for Nonlinear Sequence Modeling — arXiv:2609.35441},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35441},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3086efcdba6; sha256 4cc466193b627d4cd9976d83ffccd7107da14f53dc946eaf9bb1e283ac787b64},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35441. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

State space models (SSMs) achieve efficient sequence processing because their affine state updates are closed under composition and can therefore be evaluated with an associative parallel scan. Nonlinear recurrent models can provide richer, state-dependent dynamics, but generally lose this compositional structure: parallel evaluation then requires iterative methods that repeatedly linearize and scan the recurrence. We ask, what state-dependent nonlinear dynamics can be designed to remain exactly composable? We answer by introducing RiccatiSSM, a nonlinear SSM, in which each state dimension follows an input-conditioned Riccati differential equation. Its quadratic state dependence makes the local Jacobian explicitly state-dependent, while its exact per-step flow under piecewise-constant inputs is a Möbius transformation. Since Möbius maps are closed under composition and compose through $2\times 2$ matrix multiplication, the complete nonlinear state trajectory can be evaluated exactly with a single associative parallel scan, without iterative linearization. We further derive a constrained parameterization that ensures bounded, contractive dynamics, and avoids poles in the fractional-linear state update. Across long-sequence classification, regression, and forecasting tasks, RiccatiSSM achieves competitive predictive performance while reducing runtime by $22{-}33\%$ compared to the nonlinear LrcSSM under matched architectures. These results demonstrate that state-dependent nonlinear dynamics can retain exact composability and be evaluated efficiently within a single parallel scan.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.35441 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T20:29:03.358Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).