Metraipolis › archive › dc_b000a2bc6cbc
LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers — arXiv:2609.30973
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30973
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:13:03.521Z
- SHA-256 of the archived text
8282afe5de184162e0494ade56276b66657a49ea2a762071070bb6cb76cdd4a7- Stable URL of this page
https://metraipolis.com/documento/dc_b000a2bc6cbc
How to cite
LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers — arXiv:2609.30973 — arXiv (en), https://arxiv.org/abs/2609.30973 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b000a2bc6cbc (Metraipolis archive dc_b000a2bc6cbc, sha256 8282afe5de184162e0494ade56276b66657a49ea2a762071070bb6cb76cdd4a7)
BibTeX
@misc{dcb000a2bc6cbc,
title = {LipSSM: Structurally Lipschitz-Bounded Cascaded State-Space Model via Metric Transfer between Consecutive SSM Layers — arXiv:2609.30973},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30973},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b000a2bc6cbc; sha256 8282afe5de184162e0494ade56276b66657a49ea2a762071070bb6cb76cdd4a7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30973. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Lipschitz continuity is a fundamental principle in the design of certifiably robust deep neural networks (DNNs), wherein adjusting the Lipschitz constant, which quantifies network robustness, is of central theoretical importance. A standard approach to enforcing Lipschitz continuity requires each layer of a DNN to be Lipschitz continuous, thereby guaranteeing overall Lipschitz continuity. However, this layer-wise approach typically imposes overly conservative restrictions by producing a loose estimate of the overall Lipschitz constant, which limits the expressive capacity of the DNN and degrades empirical performance at a prescribed level of robustness. To overcome this loose estimation, the recently proposed LipKernel transfers information across layers to yield a much tighter overall Lipschitz bound than conventional layer-wise construction. In this paper, we extend this concept to cascaded state-space models (SSMs) to construct Lipschitz-continuous DNNs capable of modeling longer-term dependencies. The proposed architecture, named LipSSM, is theoretically justified and empirically evaluated. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Systems and Control (eess.SY). Pagina del lavoro: https://arxiv.org/abs/2609.30973 — 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 2026-10-08T01:43:06.718Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).