Metraipolis › archive › dc_3655cfaf32db

Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders — arXiv:2610.12370

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12370
License (as archived)
CC0-1.0
Archived
2026-10-09T06:23:45.237Z
SHA-256 of the archived text
0d1aad57c9de21dc4f70bf2411ba802b9645ebe16433c83c62741daaf863c7a6
Stable URL of this page
https://metraipolis.com/documento/dc_3655cfaf32db

How to cite

Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders — arXiv:2610.12370 — arXiv (en), https://arxiv.org/abs/2610.12370 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3655cfaf32db (Metraipolis archive dc_3655cfaf32db, sha256 0d1aad57c9de21dc4f70bf2411ba802b9645ebe16433c83c62741daaf863c7a6)
BibTeX
@misc{dc3655cfaf32db,
  title = {Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders — arXiv:2610.12370},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12370},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3655cfaf32db; sha256 0d1aad57c9de21dc4f70bf2411ba802b9645ebe16433c83c62741daaf863c7a6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12370. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Koopman operator theory provides a linear framework for analyzing nonlinear dynamical systems and has become a major tool for data-driven modeling. A central challenge, however, is that finite-dimensional approximations computed by methods such as extended dynamic mode decomposition (EDMD) require the dictionary to be specified a priori. Recent machine-learning approaches address this limitation by learning the dictionary from data, predominantly using artificial neural network (ANN) autoencoder architectures. Although kernel methods offer an alternative with greater interpretability and tractability for theoretical analysis, they have received little attention in this setting. We introduce extended dynamic mode decomposition with kernel-based dictionary learning (EDMD-kDL), a kernel-based method for learning finite-dimensional Koopman embeddings directly from data. The method combines ideas from collocation methods and bilevel optimization to simultaneously learn a kernel dictionary and the corresponding Koopman approximation. We evaluate EDMD-kDL against state-of-the-art ANN-based approaches on a range of numerical experiments, including global sea-surface-temperature forecasting and learning directly from video data. Across all tested settings, EDMD-kDL achieves performance comparable to or better than the ANN-based methods. Moreover, in contrast to standard kernel methods, the proposed approach is scalable to large datasets by design since the size of the required kernel matrices depends on the number of collocation points rather than the size of the training dataset.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Dynamical Systems (math.DS); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2610.12370 — 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 2026-10-09T05:50:31.798Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).