Metraipolis › archive › dc_22262defef63

Wavelet Flow Matching for Time Series — arXiv:2609.39374

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.39374
License (as archived): CC0-1.0
Archived: 2026-10-07T12:45:19.556Z
SHA-256 of the archived text: c293ebf69c2773376927625a85dcbd23b3a3dee4d353e3d7575eb7e740aad7ea
Stable URL of this page: https://metraipolis.com/documento/dc_22262defef63

How to cite

Wavelet Flow Matching for Time Series — arXiv:2609.39374 — arXiv (en), https://arxiv.org/abs/2609.39374 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22262defef63 (Metraipolis archive dc_22262defef63, sha256 c293ebf69c2773376927625a85dcbd23b3a3dee4d353e3d7575eb7e740aad7ea)

BibTeX

@misc{dc22262defef63,
  title = {Wavelet Flow Matching for Time Series — arXiv:2609.39374},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39374},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22262defef63; sha256 c293ebf69c2773376927625a85dcbd23b3a3dee4d353e3d7575eb7e740aad7ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39374. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthetic time series are increasingly used for data augmentation, privacy-preserving data sharing, and downstream model development, yet faithfully reproducing both multi-scale temporal structure and cross-channel dependencies remains challenging. We study multivariate time-series generation through flow matching in the wavelet domain. By operating on multilevel discrete wavelet coefficients rather than directly in the time domain, the model represents coarse structure and progressively finer details at separate scales. Their naturally different variances further induce an implicit coarse-to-fine generative process without requiring an explicit multi-scale schedule. Since the transform acts independently on each channel, we pair it with a channel-token transformer whose attention directly models cross-channel dependencies. Across seven benchmark datasets and four sequence lengths, our method is best or tied on a majority of dataset-metric combinations, with the largest and most consistent improvements in Context-FID and discriminative score.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.39374 — 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 2026-10-07T12:14:14.072Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).