Metraipolis › archive › dc_9d0fb209ea44

MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting — arXiv:2610.06039

Source
arXiv
Original
https://arxiv.org/abs/2610.06039
License (as archived)
CC0-1.0
Archived
2026-10-06T05:27:22.948Z
SHA-256 of the archived text
2b5f4b23aaea3f7d1b5837a626d18c4ef580dabe78b21ca8746e65c43b64cd01
Stable URL of this page
https://metraipolis.com/documento/dc_9d0fb209ea44

How to cite

MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting — arXiv:2610.06039 — arXiv, https://arxiv.org/abs/2610.06039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9d0fb209ea44 (Metraipolis archive dc_9d0fb209ea44, sha256 2b5f4b23aaea3f7d1b5837a626d18c4ef580dabe78b21ca8746e65c43b64cd01)
BibTeX
@misc{dc9d0fb209ea44,
  title = {MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting — arXiv:2610.06039},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06039},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9d0fb209ea44; sha256 2b5f4b23aaea3f7d1b5837a626d18c4ef580dabe78b21ca8746e65c43b64cd01},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent work has shown that probabilistic flow matching for time series forecasting benefits from a data-matched prior. The resulting prior introduces local correlations, which a sequential architecture usually absorbs: a recurrent neural network (RNN), a structured state-space model (S4), or a Transformer. However, such a backbone costs GPU memory and time per epoch. A cheaper alternative is MLP-based latent-space flow matching: embed the time series via an invertible map to a single latent vector and learn the flow there, so a tabular MLP can treat the series as a set of features. The relationship between the prior and the choice of linear latent map is understudied in conditional flow matching (CFM) forecasting, yet we found it strongly affects performance. Fixed transforms such as Fourier or discrete cosine (DCT) are only well-conditioned for Ornstein--Uhlenbeck priors, while a principal-component (PCA) map fit to the data is a strong but training-set-dependent reference sensitive to train--test shift. Instead, we propose to use the Mercer eigenbasis of the prior kernel: it diagonalises the centred covariance exactly, decouples from training data, and adapts to non-stationary and periodic priors. On five GluonTS benchmarks (ETTh1, ETTh2, Weather, Electricity, Traffic) under a shared protocol with TSFlow, the resulting MLP matches or beats it on CRPS at about $4.7\times$ less training memory and $3.5\times$--$4.4\times$ less time per epoch.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.06039 — 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 2026-10-06T05:24:06.108Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).