Metraipolis › archive › dc_c319dc12e4f7
Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling — arXiv:2609.06394
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06394
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:58:58.275Z
- SHA-256 of the archived text
3e66f30b41c9cde2b7d17f1cba9b4d910ab3f5ae394162750ea1ea245a89d96a- Stable URL of this page
https://metraipolis.com/documento/dc_c319dc12e4f7
How to cite
Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling — arXiv:2609.06394 — arXiv (en), https://arxiv.org/abs/2609.06394 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c319dc12e4f7 (Metraipolis archive dc_c319dc12e4f7, sha256 3e66f30b41c9cde2b7d17f1cba9b4d910ab3f5ae394162750ea1ea245a89d96a)
BibTeX
@misc{dcc319dc12e4f7,
title = {Beyond Worst-Case Coreset Bounds for $k$-Clustering via Determinantal Sampling — arXiv:2609.06394},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06394},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c319dc12e4f7; sha256 3e66f30b41c9cde2b7d17f1cba9b4d910ab3f5ae394162750ea1ea245a89d96a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06394. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Massive datasets in modern machine learning have made data reduction a central challenge, particularly for clustering tasks where memory and computational constraints demand compact yet faithful summaries. A standard approach is to construct an \textit{$\epsilon$-coreset}: a small weighted subset that approximately preserves the clustering cost for every plausible choice of centers. For the \textit{$(k,z)$-clustering problem}, existing worst-case bounds on coreset size are essentially tight, ruling out substantially smaller coresets in general. However, such worst-case instances are often unrepresentative of real-world data. In this work, we show that significantly smaller coresets are possible under mild and natural assumptions on the underlying data distribution. We introduce a new correlated sampling framework, called \textit{determinantal sampling}, based on a novel application of determinantal point processes. Using this framework, we obtain an efficiently constructible $\varepsilon$-coreset for $(k,z)$-clustering in $\mathbb R^d$ whose dependence on $1/\varepsilon$ has exponent strictly smaller than $2$ when $d$ is fixed. This improves over the worst-case $\varepsilon^{-2}$ barrier under our beyond-worst-case assumptions. To the best of our knowledge, this is the first result that provably surpasses these lower bounds through beyond-worst-case assumptions. Finally, we validate our approach on synthetic and real-world benchmark datasets, where it consistently achieves smaller coresets than existing state-of-the-art methods, even without explicitly enforcing the assumptions used in the analysis.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Probability (math.PR).
Pagina del lavoro: https://arxiv.org/abs/2609.06394 — 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 2026-10-16T13:39:43.170Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).