Metraipolis › archive › dc_60522c1cd2cc
Generative sequence modeling for infinite memory processes via predictive states — arXiv:2609.38524
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38524
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:47:15.801Z
- SHA-256 of the archived text
b99a6f72204062bb90299e6b59f42dc4ae44c753bf66d0b7b9424e40a03f5cb3- Stable URL of this page
https://metraipolis.com/documento/dc_60522c1cd2cc
How to cite
Generative sequence modeling for infinite memory processes via predictive states — arXiv:2609.38524 — arXiv (en), https://arxiv.org/abs/2609.38524 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_60522c1cd2cc (Metraipolis archive dc_60522c1cd2cc, sha256 b99a6f72204062bb90299e6b59f42dc4ae44c753bf66d0b7b9424e40a03f5cb3)
BibTeX
@misc{dc60522c1cd2cc,
title = {Generative sequence modeling for infinite memory processes via predictive states — arXiv:2609.38524},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38524},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_60522c1cd2cc; sha256 b99a6f72204062bb90299e6b59f42dc4ae44c753bf66d0b7b9424e40a03f5cb3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38524. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We consider estimating the one-step-ahead conditional distribution of a multivariate stochastic process. Many existing approaches rely on assumptions such as finite-range memory, sparsity, or additivity, which can be poorly suited to processes with long-range nonlinear interactions. However, without such structural assumptions, nonparametric estimation is challenging due to the curse of dimensionality. To address this challenge, we introduce a new estimation approach based on the predictive states of a process, possibly with infinite-range memory. We show that our estimator achieves fast convergence rates when the past history can be compressed into a low-dimensional statistic that is sufficient for predicting the future. Specifically, we show that the statistical complexity of the estimation problem is determined by the intrinsic dimension of the predictive state space. We establish guarantees for an instantiation of our method based on deep neural network estimators, and we support these theoretical results with experiments. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Methodology (stat.ME). Pagina del lavoro: https://arxiv.org/abs/2609.38524 — 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 2026-10-07T13:18:10.574Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).