Metraipolis › archive › dc_3d21662011e2
Training and Scaling Compute-Optimal Physiological Waveform Foundation Models — arXiv:2610.05649
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05649
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:31:12.137Z
- SHA-256 of the archived text
69db18f86539c1be300fa21a90dcfd669d52a92263c56627ff6e1356c637bdf5- Stable URL of this page
https://metraipolis.com/documento/dc_3d21662011e2
How to cite
Training and Scaling Compute-Optimal Physiological Waveform Foundation Models — arXiv:2610.05649 — arXiv, https://arxiv.org/abs/2610.05649 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3d21662011e2 (Metraipolis archive dc_3d21662011e2, sha256 69db18f86539c1be300fa21a90dcfd669d52a92263c56627ff6e1356c637bdf5)
BibTeX
@misc{dc3d21662011e2,
title = {Training and Scaling Compute-Optimal Physiological Waveform Foundation Models — arXiv:2610.05649},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05649},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3d21662011e2; sha256 69db18f86539c1be300fa21a90dcfd669d52a92263c56627ff6e1356c637bdf5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05649. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We investigate the scaling laws and compute-optimal training of physiological waveform foundation models (FMs). We train Aether, a family of over one hundred FMs ranging from 20M to 2.1B parameters, on up to 36.3M hours of physiological waveforms. We construct eight clinical prediction tasks from MIMIC-III and evaluate the FMs through linear probing. The 720M FM outperforms all existing baseline FMs across all eight tasks. A scaling law of model size, pretraining hours, and labeled patients predicts downstream ranking error, i.e. $1-\mathrm{AUROC}$, effectively with $0.5\%$ prediction MAE at held-out resource scales and $0.9\%$ MAE when extrapolating to 2.1B parameters. We present three findings: (1) Compute-optimal training scales both FM size and pretraining hours. Under the fitted law, a $10.0\times$ increase in compute FLOPs scales model size by $1.2\times$ and pretraining hours by $8.2\times$. (2) Larger FMs use waveform data more efficiently, and greater pretraining exposure increases the benefit of model scaling. Starting from 25M parameters and 4.8M pretraining hours, doubling FM size reduces the predicted hours needed for the same performance by $51.8\%$. (3) Pretraining and clinical supervision reinforce each other: more labeled patients increase the return to pretraining, while larger FMs and longer pretraining reduce labeling requirements. For the example of the 720M FM, extending pretraining from 120K to 36.3M hours reduces the predicted patient requirement by $61\%$ at a target ranking error. These findings provide a quantitative training recipe and a promising and durable scaling path for physiological waveform modeling and downstream clinical prediction.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05649 — 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 2026-10-06T05:27:05.814Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).