Metraipolis › archive › dc_1b581ccebc65
DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting — arXiv:2609.32363
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.32363
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:00:07.725Z
- SHA-256 of the archived text
dd49c0d5251a58c1666fecb6ad4b1a8a3a781e8e6172d5165d133102aea486de- Stable URL of this page
https://metraipolis.com/documento/dc_1b581ccebc65
How to cite
DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting — arXiv:2609.32363 — arXiv (en), https://arxiv.org/abs/2609.32363 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1b581ccebc65 (Metraipolis archive dc_1b581ccebc65, sha256 dd49c0d5251a58c1666fecb6ad4b1a8a3a781e8e6172d5165d133102aea486de)
BibTeX
@misc{dc1b581ccebc65,
title = {DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting — arXiv:2609.32363},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.32363},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1b581ccebc65; sha256 dd49c0d5251a58c1666fecb6ad4b1a8a3a781e8e6172d5165d133102aea486de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32363. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Probabilistic time series forecasting requires modeling and predicting complex and time-varying distributions. Recently, Denoising Diffusion Probabilistic Model (DDPM)-based approaches have shown promise by equipping the dif- fusion process with pretrained mean and variance estimators to accommodate distributional shift. However, these methods typically follow the standard DDPM framework and consider only partial components of the evidence lower bound (ELBO), treating the training of estimators as designed regression tasks separate from the variational inference framework. To address this, we rethink the ELBO under the Location-Scale Noise Model (LSNM) and find that it naturally induces a Gaussian negative log likelihood objective for the estimators and inherently defines a joint training objective that unifies recent diffusion paradigms for probabilistic forecasting. Building on this principled ELBO reformulation, we propose Diff- PTS, a general framework that enables end-to-end optimization of all components within the ELBO. Across multiple benchmarks, DiffPTS consistently outperforms recent models, achieving state-of-the-art performance with an average CRPS/MSE reduction of over 14.53%/16.55% compared to existing diffusion-based methods. The code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.32363 — 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 2026-10-07T20:29:02.312Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).