Metraipolis › archive › dc_aededd556b9f

TopTimeNet: Topologically-assisted time-series classification model — arXiv:2609.39792

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39792
License (as archived)
CC0-1.0
Archived
2026-10-07T13:46:37.115Z
SHA-256 of the archived text
3bc19a08f6ab45ee100b93f220bdf442d4f506f01b2e8f86ca513dd7d274aae6
Stable URL of this page
https://metraipolis.com/documento/dc_aededd556b9f

How to cite

TopTimeNet: Topologically-assisted time-series classification model — arXiv:2609.39792 — arXiv (en), https://arxiv.org/abs/2609.39792 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aededd556b9f (Metraipolis archive dc_aededd556b9f, sha256 3bc19a08f6ab45ee100b93f220bdf442d4f506f01b2e8f86ca513dd7d274aae6)
BibTeX
@misc{dcaededd556b9f,
  title = {TopTimeNet: Topologically-assisted time-series classification model — arXiv:2609.39792},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39792},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aededd556b9f; sha256 3bc19a08f6ab45ee100b93f220bdf442d4f506f01b2e8f86ca513dd7d274aae6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39792. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Distinguishing periodic from chaotic dynamics in a time series is a fundamental challenge in both physics and engineering. Yet, end-to-end learned architectures must discover both a representation and a decision boundary from data, at substantial cost. We introduce TopTimeNet, which decouples these tasks: a fixed, non-learned stage extracts a $42$-dimensional geometric and topological descriptor from Takens delay embeddings and persistent homology, and a lightweight learnable stage performs classification. On a benchmark of $49$ nonlinear dynamical systems, a $1{,}638$-parameter configuration matches the mean accuracy of one with $33\times$ more trainable parameters. Additionally, this approach delivers mean accuracy comparable to convolutional neural networks and surpasses the average performance of converged Transformer models, while requiring three to four orders of magnitude fewer trainable parameters. Robustness also depends sharply on where noise is introduced: TopTimeNet degrades gracefully under perturbations to its precomputed features, but degrades sharply when noise is introduced into the raw signal and the full feature-extraction pipeline is recomputed, showing that robustness to perturbations of the precomputed features does not imply robustness of the complete raw-signal-to-prediction pipeline. These results show that decoupling fixed geometric and topological feature construction from a lightweight discriminative stage can achieve comparable classification accuracy with substantially fewer trainable parameters.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Geometry (cs.CG); Dynamical Systems (math.DS); Chaotic Dynamics (nlin.CD); Applied Physics (physics.app-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.39792 — 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 2026-10-07T13:18:10.454Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).