Metraipolis › archive › dc_6a98bf8a8420

Forward-Evolution Error Analysis and Adaptive Design for Matrix-Valued Diffusion Models — arXiv:2608.15103

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15103
License (as archived)
CC0-1.0
Archived
2026-10-18T20:19:56.479Z
SHA-256 of the archived text
57785487d74985bd61f95e59650073e74347cb8867e9e5672b4a69b231631696
Stable URL of this page
https://metraipolis.com/documento/dc_6a98bf8a8420

How to cite

Forward-Evolution Error Analysis and Adaptive Design for Matrix-Valued Diffusion Models — arXiv:2608.15103 — arXiv (en), https://arxiv.org/abs/2608.15103 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6a98bf8a8420 (Metraipolis archive dc_6a98bf8a8420, sha256 57785487d74985bd61f95e59650073e74347cb8867e9e5672b4a69b231631696)
BibTeX
@misc{dc6a98bf8a8420,
  title = {Forward-Evolution Error Analysis and Adaptive Design for Matrix-Valued Diffusion Models — arXiv:2608.15103},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15103},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6a98bf8a8420; sha256 57785487d74985bd61f95e59650073e74347cb8867e9e5672b4a69b231631696},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15103. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models learn to reverse a predefined corruption process, but sampling still requires a costly time discretization and depends on the chosen noise schedule. We study these two issues for variance-preserving diffusions with matrix-valued schedules. Our analysis transfers reverse-time discretization errors to the forward corruption law and treats two numerical schemes within a common framework. The first freezes the score and yields, through a matrix-sensitive local comparison and forward information dissipation, an ambient-dimensional step complexity with leading factor $d/\varepsilon^2$ for KL accuracy $\varepsilon^2$. The second keeps the known Gaussian drift exact and freezes the posterior mean. For data of metric-entropy dimension $k$, a forward Markov identity, an anisotropic covering estimate, and Stieltjes integration by parts give the corresponding factor $k\log k/\varepsilon^2$. In both cases, the proof identifies a local error, accumulates it through the forward evolution, and inserts the result into a common KL decomposition. The local errors further provide directional criteria for matrix schedules and an asymptotically optimal square-root adaptive grid. A high-dimensional Gaussian-mixture experiment illustrates the resulting schedule and grid improvements.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-18 in math.ST).
Categorie arXiv: Statistics Theory (math.ST) ; Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2608.15103 — 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 2026-10-18T19:45:21.121Z dalla pagina https://arxiv.org/catchup/math.ST/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).