Metraipolis › archive › dc_973ec5b59314
LoRA-RC: Reservoir Computing with Low-Rank Adaptation — arXiv:2609.12327
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12327
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:02:40.582Z
- SHA-256 of the archived text
aead0a732fbc5ba217582878b90f3fb8d123b7ca80808a233d92638114442803- Stable URL of this page
https://metraipolis.com/documento/dc_973ec5b59314
How to cite
LoRA-RC: Reservoir Computing with Low-Rank Adaptation — arXiv:2609.12327 — arXiv (en), https://arxiv.org/abs/2609.12327 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_973ec5b59314 (Metraipolis archive dc_973ec5b59314, sha256 aead0a732fbc5ba217582878b90f3fb8d123b7ca80808a233d92638114442803)
BibTeX
@misc{dc973ec5b59314,
title = {LoRA-RC: Reservoir Computing with Low-Rank Adaptation — arXiv:2609.12327},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12327},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_973ec5b59314; sha256 aead0a732fbc5ba217582878b90f3fb8d123b7ca80808a233d92638114442803},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12327. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reservoir computing (RC) trains only a linear readout over a fixed recurrent layer, making it fast and data-efficient for online prediction. However, a static reservoir degrades under system drift, readout-only adaptation is then insufficient, and unconstrained reservoir adaptation can destroy the echo-state and incremental stability properties that make RC reliable. This paper proposes LoRA-RC, which adapts the recurrent matrix through a low-rank correction driven by streaming prediction errors. The base reservoir and adaptation bases are fixed offline; a small core matrix is adapted online, projected onto a spectral-norm ball, and low-pass filtered at each step. The projection guarantees that every applied recurrent matrix remains within a certified contraction set, and an incremental input-to-state stability bound is established for the reservoir along each online adaptation path, with path-independent rate and gain. On a Lorenz system with an abrupt parameter drift, LoRA-RC cuts post-drift prediction error by 56% versus a fixed RC and 51% versus readout-only adaptation; ablations over 20 seeds show that removing the projection inflates this error by more than a factor of 40. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Systems and Control (eess.SY); Dynamical Systems (math.DS). Pagina del lavoro: https://arxiv.org/abs/2609.12327 — 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 2026-10-16T02:51:27.777Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).