Metraipolis › archive › dc_15530cda5055
Sparse Priors for Efficient Distribution Learning — arXiv:2609.20883
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20883
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T01:44:29.415Z
- SHA-256 of the archived text
1ebba23a97f6c03d2a5880c3b3ec68341fc25038fd5cc963fe89756a390cea91- Stable URL of this page
https://metraipolis.com/documento/dc_15530cda5055
How to cite
Sparse Priors for Efficient Distribution Learning — arXiv:2609.20883 — arXiv (en), https://arxiv.org/abs/2609.20883 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_15530cda5055 (Metraipolis archive dc_15530cda5055, sha256 1ebba23a97f6c03d2a5880c3b3ec68341fc25038fd5cc963fe89756a390cea91)
BibTeX
@misc{dc15530cda5055,
title = {Sparse Priors for Efficient Distribution Learning — arXiv:2609.20883},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20883},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_15530cda5055; sha256 1ebba23a97f6c03d2a5880c3b3ec68341fc25038fd5cc963fe89756a390cea91},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20883. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Despite the widespread use and success of generative AI techniques today, theoretical guarantees on learning a distribution supported in $d$ dimensions from $n$ samples degrade as $O(n^{-1/\Theta(d)})$, though shown to be minimax optimal. We hypothesize that present bounds are too pessimistic because smoothness assumptions are not enough to capture the structure of distributions that often appear in real applications. Consequently, we introduce the class of sparse priors and define the "Sparse Dimension" as a measure of sparsity of a prior over the space of all distributions. We show that distribution learning under a $k$-sparse prior achieves a Bayesian risk lower bound of $\Omega(\sqrt{k/n})$ under common distance metrics, and show a matching (up to logarithmic terms asymptotically in $n,k$) upper bound for the TV distance under mild additional assumptions. We show the statistical equivalence of distribution learning and learning to sample in the Bayesian setting so that our results apply to learning to sample as well. While $k$ can still depend on the dimension $d$, or a notion of intrinsic dimension, our results show that learning under an appropriate prior overcomes the curse of dimensionality with respect to the dependence on $n$.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.20883 — 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 2026-10-10T01:14:16.589Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).