Metraipolis › archive › dc_a620f0d01aef

Finite-Time Online Sample Complexity for Conditional Diffusion Models — arXiv:2611.01562

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01562
License (as archived)
CC0-1.0
Archived
2026-11-03T10:47:42.660Z
SHA-256 of the archived text
ddce98121bb1c2b4a227c27ea3cdef3d5043081ff86d53a7361db65b1d90b8f2
Stable URL of this page
https://metraipolis.com/documento/dc_a620f0d01aef

How to cite

Finite-Time Online Sample Complexity for Conditional Diffusion Models — arXiv:2611.01562 — arXiv (en), https://arxiv.org/abs/2611.01562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a620f0d01aef (Metraipolis archive dc_a620f0d01aef, sha256 ddce98121bb1c2b4a227c27ea3cdef3d5043081ff86d53a7361db65b1d90b8f2)
BibTeX
@misc{dca620f0d01aef,
  title = {Finite-Time Online Sample Complexity for Conditional Diffusion Models — arXiv:2611.01562},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01562},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a620f0d01aef; sha256 ddce98121bb1c2b4a227c27ea3cdef3d5043081ff86d53a7361db65b1d90b8f2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the finite-time training and sampling error of conditional diffusion models trained by online stochastic-gradient denoising score matching. Rather than assuming access to an exact empirical or population risk minimizer, we analyze the score network produced after a finite number of stochastic-gradient updates under an explicit localized Polyak--Łojasiewicz (PL) condition, stochastic-gradient regularity, and a trajectory-containment assumption. Our analysis separates the network approximation complexity from the online training-sample budget and propagates both errors through the reverse diffusion process. Under anisotropic smoothness, a joint intrinsic-dimensional structure for the data and conditioning variables, sub-exponential tails, and explicit approximation-class compatibility, we obtain a conditional score approximation error of order \[ \widetilde{\mathcal O}\!\left(M^{-\eta_{\mathrm{app}}}\right), \qquad \eta_{\mathrm{app}} = \frac{2\alpha_x} {2\alpha_x+d_x'+(\alpha_x/\alpha_y)d_y'}, \] where \(M\) denotes the approximation complexity, \(d_x'\) and \(d_y'\) are the intrinsic response and conditioning dimensions, and \(\alpha_x,\alpha_y\) are their corresponding smoothness exponents. For \(N=RB\) online denoising samples used by SGD, the finite-time optimization error is controlled explicitly in terms of the PL, smoothness, gradient-noise, and initialization constants. Combining these ingredients with reverse-process stability yields a total-variation bound that decomposes into terminal-initialization, time-discretization, approximation/localization, and finite-time optimization errors.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01562 — 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 2026-11-03T10:39:50.487Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).