Metraipolis › archive › dc_8eaba8bcdeb6

Discrete Diffusion Models are Minimax Optimal Under Sparsity — arXiv:2610.19020

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19020
License (as archived)
CC0-1.0
Archived
2026-10-15T14:23:12.121Z
SHA-256 of the archived text
95ffc14b3fb2d3291079d927110508f372bf069797508292b051e26cbd76b802
Stable URL of this page
https://metraipolis.com/documento/dc_8eaba8bcdeb6

How to cite

Discrete Diffusion Models are Minimax Optimal Under Sparsity — arXiv:2610.19020 — arXiv (en), https://arxiv.org/abs/2610.19020 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8eaba8bcdeb6 (Metraipolis archive dc_8eaba8bcdeb6, sha256 95ffc14b3fb2d3291079d927110508f372bf069797508292b051e26cbd76b802)
BibTeX
@misc{dc8eaba8bcdeb6,
  title = {Discrete Diffusion Models are Minimax Optimal Under Sparsity — arXiv:2610.19020},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19020},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8eaba8bcdeb6; sha256 95ffc14b3fb2d3291079d927110508f372bf069797508292b051e26cbd76b802},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19020. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Discrete diffusion models have emerged as a leading alternative to autoregressive models for generating text and other categorical data, yet their theoretical foundations remain less developed than those of their continuous counterparts. For continuous diffusion models, a prominent line of theory suggests that these models can adapt to low-dimensional structure in the data, thereby improving statistical efficiency and generalization. In this work, we investigate the discrete analogue of this phenomenon by studying the statistical rates of discrete diffusion models under sparsity assumptions. By analyzing a nonparametric estimator derived from a regularized score-entropy objective, we establish minimax-optimal rates in the sparse regime. The proposed regularization can be viewed as an adaptation of label smoothing techniques introduced for classification, and does not require the knowledge of the sparsity parameter. This shows that discrete diffusion models can adapt intrinsically to sparsity.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.19020 — 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 2026-10-15T13:53:35.816Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).