Metraipolis › archive › dc_22e07b41d33a

Diffusion Models for High-Dimensional Clustered Data: Intrinsic-Dimension Adaptivity via Bayesian Classification — arXiv:2608.19067

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19067
License (as archived)
CC0-1.0
Archived
2026-10-18T13:53:54.030Z
SHA-256 of the archived text
16248f0d7fd8d11986811773440420b803f4ead4a4acb5135e07055e307316a4
Stable URL of this page
https://metraipolis.com/documento/dc_22e07b41d33a

How to cite

Diffusion Models for High-Dimensional Clustered Data: Intrinsic-Dimension Adaptivity via Bayesian Classification — arXiv:2608.19067 — arXiv (en), https://arxiv.org/abs/2608.19067 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22e07b41d33a (Metraipolis archive dc_22e07b41d33a, sha256 16248f0d7fd8d11986811773440420b803f4ead4a4acb5135e07055e307316a4)
BibTeX
@misc{dc22e07b41d33a,
  title = {Diffusion Models for High-Dimensional Clustered Data: Intrinsic-Dimension Adaptivity via Bayesian Classification — arXiv:2608.19067},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19067},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22e07b41d33a; sha256 16248f0d7fd8d11986811773440420b803f4ead4a4acb5135e07055e307316a4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19067. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The empirical success of diffusion models in generative modelling has motivated theoretical work, including quantitative error bounds and qualitative analyses that characterise the different phases of denoising. We bring these two areas together by studying the adaptivity of diffusion models to the structured geometry of multimodal high-dimensional data that consists of multiple clusters in $\mathbb{R}^D$, each with its own low-dimensional structure, and inter-cluster separation depending on $D$. We employ $K$-mixture Gaussian distributions as a canonical framework to capture this geometry and establish two theoretical results. First, we interpret denoising as a dynamical Bayesian classifier: the mixture score is a posterior-weighted average of cluster-wise scores, and we show that, with high probability, the posterior class probabilities concentrate on a single cluster once the signal-to-noise ratio reaches the scale $\Theta (\log (KD)/D)$. Second, by separately analysing the denoising process in its mixing and cluster-commitment phases, we prove that the KL error bound depends linearly on the maximum intrinsic dimension of a cluster, up to a logarithmic factor, even when $K$ grows polynomially with $D$. This improves on ambient-dimensional bounds and extends existing low-dimensional adaptivity analyses to multimodal distributions with heterogeneous, approximately low-rank covariances.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-20 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2608.19067 — 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 2026-10-18T13:50:59.007Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).