Metraipolis › archive › dc_ff42fbf7f7ef

Sobolev Regularized Score Difference Estimation in Diffusion Models — arXiv:2608.18237

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.18237
License (as archived)
CC0-1.0
Archived
2026-10-18T13:53:43.944Z
SHA-256 of the archived text
26f45c431c64ff75afe5d3b29c09a11718e0ef1ec2658f9f941f8f116805d2e8
Stable URL of this page
https://metraipolis.com/documento/dc_ff42fbf7f7ef

How to cite

Sobolev Regularized Score Difference Estimation in Diffusion Models — arXiv:2608.18237 — arXiv (en), https://arxiv.org/abs/2608.18237 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff42fbf7f7ef (Metraipolis archive dc_ff42fbf7f7ef, sha256 26f45c431c64ff75afe5d3b29c09a11718e0ef1ec2658f9f941f8f116805d2e8)
BibTeX
@misc{dcff42fbf7f7ef,
  title = {Sobolev Regularized Score Difference Estimation in Diffusion Models — arXiv:2608.18237},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.18237},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff42fbf7f7ef; sha256 26f45c431c64ff75afe5d3b29c09a11718e0ef1ec2658f9f941f8f116805d2e8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18237. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling. In particular, score differences arise naturally in transfer learning, where the score difference provides the mechanism for adapting a pre-trained model to a new target distribution, and in diffusion model-based post-training methods such as discriminator guidance. Existing estimators for score differences in these settings either lack of statistical consistency or are difficult to scale up in high-dimensions. We propose a statistically consistent and scalable estimator for score differences based on Sobolev regularization, which plays a crucial role in ensuring consistency and stablizing the training in the small-sample regime. Mathematically, we establish a convergence rate of $O(n^{-\frac{s-1}{d+2s-2}})$ where $d$ is the dimension and $s$ denotes the smoothness of the underlying densities, and provide a minimax lower bound of $\tilde{\Omega}(n^{-\frac{2(s-1)}{d+2s}})$ (in mean-squared error). Empirically, our estimator exhibits significantly improved stability in small-sample regimes compared to existing methods. We demonstrate its effectiveness on real-world tasks, including transfer learning for ECG signal generation, where it substantially outperforms non-regularized score difference estimators in downstream classification performance.

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); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.18237 — 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 2026-10-18T13:50:58.983Z 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).