Metraipolis › archive › dc_2966d652f011
Sliced Wasserstein Sketches with Error Certificates — arXiv:2610.20788
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20788
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:20:02.090Z
- SHA-256 of the archived text
f63114f1321249d0eb90265683a82a4e0860dd6cf5f8b88f672001430bc52b2a- Stable URL of this page
https://metraipolis.com/documento/dc_2966d652f011
How to cite
Sliced Wasserstein Sketches with Error Certificates — arXiv:2610.20788 — arXiv (en), https://arxiv.org/abs/2610.20788 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2966d652f011 (Metraipolis archive dc_2966d652f011, sha256 f63114f1321249d0eb90265683a82a4e0860dd6cf5f8b88f672001430bc52b2a)
BibTeX
@misc{dc2966d652f011,
title = {Sliced Wasserstein Sketches with Error Certificates — arXiv:2610.20788},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20788},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2966d652f011; sha256 f63114f1321249d0eb90265683a82a4e0860dd6cf5f8b88f672001430bc52b2a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20788. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Compact representations that support geometrically meaningful comparisons are valuable for learning from probability distributions. We study optimal, free-weight $M$-atom quantization of one-dimensional probability measures in quadratic Wasserstein distance and extend it to higher dimensions via slicing. Using $L$ shared projections yields a sketch with $O(LM)$ comparison time. Our main result is an exact decomposition of squared distance error into residual and partition-mismatch terms, yielding computable certificates for arbitrary centroid sketches. For optimal sketches, a finite $(2+\delta)$ moment for some $\delta>0$ guarantees $O(M^{-1})$ error in the finite-direction sliced distance, while equal-mass sketches can converge more slowly. Each slice preserves its mean, while storing residual energies enables covariance recovery from sufficiently many generic directions. Experiments on document, point-cloud, and flow-cytometry benchmarks show that optimal sketches substantially reduce storage while preserving the classification performance of uncompressed sliced distances. They also improve generalization from few labelled subjects and support end-to-end learning as compact pooling layers.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.20788 — 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 2026-10-16T08:48:02.654Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).