Metraipolis › archive › dc_411e322fcfbe
A KKL Observer Perspective on Reservoir Computing — arXiv:2610.04343
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04343
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:32:05.739Z
- SHA-256 of the archived text
a636cad14f77eabde48f2d1243ca950223c97467ed695f572f698469fd22f672- Stable URL of this page
https://metraipolis.com/documento/dc_411e322fcfbe
How to cite
A KKL Observer Perspective on Reservoir Computing — arXiv:2610.04343 — arXiv, https://arxiv.org/abs/2610.04343 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_411e322fcfbe (Metraipolis archive dc_411e322fcfbe, sha256 a636cad14f77eabde48f2d1243ca950223c97467ed695f572f698469fd22f672)
BibTeX
@misc{dc411e322fcfbe,
title = {A KKL Observer Perspective on Reservoir Computing — arXiv:2610.04343},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04343},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_411e322fcfbe; sha256 a636cad14f77eabde48f2d1243ca950223c97467ed695f572f698469fd22f672},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04343. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reservoir computing (RC) is a machine learning technique for data-driven modeling of dynamics for forecasting and control, primarily studied in computer science and physics literature with promising applications in neural network learning, physical computing, and neuroscience. Why reservoirs learn and how to choose good reservoir architectures are considered important open questions. We show that the RC problem is mathematically an extension of a classic problem in systems and control theory, the Kazantzis-Kravaris-Luenberger (KKL) observer design problem. As a consequence, many of the questions considered open for RC stand to benefit from a large body of theory in the mature KKL literature, non-exhaustively including on questions of embedding, transverse stability, local and global uniqueness guarantees, and effective data-driven solution constructions. Elaborating on this connection, we show that the surprising forecasting ability of reservoirs is in fact a direct consequence of the well-known observer internal model principle, derive an upper bound on the prediction error over a fixed forecast horizon, and provide a partial explanation for why linear readout training in RC works reasonably well. This work illustrates how classical ideas from systems and control can provide strong theoretical backing and open new questions for modern machine learning methods. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG); Dynamical Systems (math.DS); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2610.04343 — 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 2026-10-06T05:27:05.959Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).