Metraipolis › archive › dc_3a12d386cf2f
PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders — arXiv:2609.05212
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.05212
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T23:00:11.805Z
- SHA-256 of the archived text
76f88e97e77ab50bf3b047c081d14f5c2a00c231cbef8af3a21068e04c2ca833- Stable URL of this page
https://metraipolis.com/documento/dc_3a12d386cf2f
How to cite
PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders — arXiv:2609.05212 — arXiv (en), https://arxiv.org/abs/2609.05212 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3a12d386cf2f (Metraipolis archive dc_3a12d386cf2f, sha256 76f88e97e77ab50bf3b047c081d14f5c2a00c231cbef8af3a21068e04c2ca833)
BibTeX
@misc{dc3a12d386cf2f,
title = {PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders — arXiv:2609.05212},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.05212},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3a12d386cf2f; sha256 76f88e97e77ab50bf3b047c081d14f5c2a00c231cbef8af3a21068e04c2ca833},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05212. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Forecasting time series accurately is critical for applications with complex data ranging from energy systems to healthcare and finance. Among current state of the art models, generative latent variable models are increasingly implemented; yet principled generalisation guarantees for modern latent variable models remain limited. In particular, while Variational AutoEncoders are widely used for sequential data, their theoretical analysis is largely restricted to i.i.d. settings. In this work, we develop a PAC-Bayesian framework for latent variables models applied to time series. Building on reconstruction-based bounds, we extend PAC-Bayesian guarantees to Markovian latent structures, capturing temporal dependencies through a sequential generative process. These guarantees do not grow with the length of the trajectory. Our bounds depend on assumptions which are common in the literature; we provide an example framework where they would be verified to show that they are not as restrictive as they may seem. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.05212 — 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 2026-10-16T22:31:32.249Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).