Metraipolis › archive › dc_567c4bc41de4
Discretizing Continuous Time Series for Imputation with Masked Diffusion Training — arXiv:2608.19119
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19119
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T13:45:35.031Z
- SHA-256 of the archived text
1b4172500de24a9e43c99427597fd0a462c93838926c3da436b94d2dd7b670bf- Stable URL of this page
https://metraipolis.com/documento/dc_567c4bc41de4
How to cite
Discretizing Continuous Time Series for Imputation with Masked Diffusion Training — arXiv:2608.19119 — arXiv (en), https://arxiv.org/abs/2608.19119 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_567c4bc41de4 (Metraipolis archive dc_567c4bc41de4, sha256 1b4172500de24a9e43c99427597fd0a462c93838926c3da436b94d2dd7b670bf)
BibTeX
@misc{dc567c4bc41de4,
title = {Discretizing Continuous Time Series for Imputation with Masked Diffusion Training — arXiv:2608.19119},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19119},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_567c4bc41de4; sha256 1b4172500de24a9e43c99427597fd0a462c93838926c3da436b94d2dd7b670bf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19119. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data. Existing approaches, however, exhibit two limitations: missing and observed values are embedded within the same representation space without explicit structural separation, and continuous diffusion-based methods are trained to predict added noise rather than the original signal. To address these, we propose the Masked Diffusion Time-series Imputation Model (MDTIM), which leverages the training paradigm of masked diffusion model for imputation tasks. The MASK token is structurally orthogonal to valid observations, and the model directly predicts the original values, naturally aligning both the representation and the learning objective with the imputation task. To bridge the gap between discrete masked diffusion and the continuous, ordinal nature of time series, we further introduce Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics. Our experiments on diverse benchmarks confirm that MDTIM achieves superior robustness and scalability, consistently outperforming state-of-the-art deterministic and generative baselines across various missing scenarios. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.19119 — 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 2026-10-18T13:41:18.001Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).