Metraipolis › archive › dc_0bdf86c8fa12
HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling — arXiv:2609.34511
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34511
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:38:22.014Z
- SHA-256 of the archived text
2ea7f9be672c17610c3f2762819b51d0921d972895648b748fc72d4f29abee9d- Stable URL of this page
https://metraipolis.com/documento/dc_0bdf86c8fa12
How to cite
HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling — arXiv:2609.34511 — arXiv (en), https://arxiv.org/abs/2609.34511 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0bdf86c8fa12 (Metraipolis archive dc_0bdf86c8fa12, sha256 2ea7f9be672c17610c3f2762819b51d0921d972895648b748fc72d4f29abee9d)
BibTeX
@misc{dc0bdf86c8fa12,
title = {HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling — arXiv:2609.34511},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34511},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0bdf86c8fa12; sha256 2ea7f9be672c17610c3f2762819b51d0921d972895648b748fc72d4f29abee9d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34511. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Most existing time series generators rely on a two-stage modeling paradigm: the first stage learns discrete latent representations of time series; the second stage performs autoregressive modeling on these discrete latents through next token prediction. However, this paradigm suffers from two stage-specific limitations: the first stage can lead to information loss when discretizing continuous time series, while the second stage is prone to error accumulation during autoregressive generation. To address these limitations, our core idea is to perform generative modeling in a continuous latent space with a more efficient autoregressive framework. We propose HALO, which enhances time series generation via Hyperspherical Latents and Masked Autoregressive modeling to achieve this goal by tackling two key bottlenecks: (1) variance and scale heterogeneity of continuous latent representations; (2) the difficulty of balancing generation efficiency with temporal correlation modeling. HALO first introduces a hyperspherical VAE that constrains continuous latents to a fixed-radius hyperspherical shell, effectively stabilizing the numerical fluctuations of continuous latent representations. Secondly, we develop a masked autoregressive model that balances parallel decoding and temporal correlation learning, substantially reducing the number of inference steps required for generation and improving generation stability. Our extensive experiments demonstrate that HALO achieves state-of-the-art generation performance while offering significantly improved inference efficiency over existing advanced baselines. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.34511 — 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 2026-10-07T22:14:28.218Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).