Metraipolis › archive › dc_3ead004da8f9

Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems — arXiv:2608.18918

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18918
License (as archived)
CC0-1.0
Archived
2026-10-18T13:53:31.717Z
SHA-256 of the archived text
606ea464a4d24247cafef9264af9a4f8d12f1c1e361022db1733e72adcda7769
Stable URL of this page
https://metraipolis.com/documento/dc_3ead004da8f9

How to cite

Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems — arXiv:2608.18918 — arXiv (en), https://arxiv.org/abs/2608.18918 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ead004da8f9 (Metraipolis archive dc_3ead004da8f9, sha256 606ea464a4d24247cafef9264af9a4f8d12f1c1e361022db1733e72adcda7769)
BibTeX
@misc{dc3ead004da8f9,
  title = {Score the Algebra, Not the Span: Dimension Reduction for Transfer Operator Models of Dynamical Systems — arXiv:2608.18918},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18918},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ead004da8f9; sha256 606ea464a4d24247cafef9264af9a4f8d12f1c1e361022db1733e72adcda7769},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18918. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Dimension reduction for dynamical systems is standard practice, and the standard route is spectral: model the transfer (Koopman) operator by its leading modes. We show that on systems assembled from several weakly interacting components --- a structure common in physical and biological settings --- this may either require an exponential number of modes, or drop an entire component: the component is absent from the model rather than modeled coarsely, and no function of it can be predicted at any accuracy. We call this linear masking. The cause is that a rank-based model pays one coordinate per mode. We propose to score instead the $\sigma$-algebra the coordinates generate, so that products and powers come free and a component's cost is governed only by its generators rather than by all its interactions. The criterion is a $\chi^2$-divergence between the embedded present and future, and it carries a budget guarantee: twice the intrinsic dimension of the dynamics is enough coordinates for an embedding whose algebra carries the operator's entire spectrum, with its full infinite rank. In variational form the criterion admits off-the-shelf estimators, and restricting its critic to the bilinear class returns the VAMP score on the span, so rank-based methods are one end of the same family. We demonstrate the proposed objective on a composite of published benchmark systems. We exhibit examples where the rank-based methods completely miss the masked components at all ranks $k<100$, while ten algebra coordinates recover all of them. In addition, the resulting algebra representation supports predicting the masked components from few labels, while direct regression from the high-dimensional observation or from the VAMP features fail.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.18918 — 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 2026-10-18T13:50:58.951Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).