Metraipolis › archive › dc_8bba00ffd81a

GEM-KMeans: Memory-Efficient and Accurate Clustering on Massive Scale with GPU Optimization — arXiv:2609.36074

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36074
License (as archived)
CC0-1.0
Archived
2026-10-07T16:59:19.223Z
SHA-256 of the archived text
940b4dea22e824ee3aa56f049bcc91c87c87affc0d717b6f27bea3deb16ef35e
Stable URL of this page
https://metraipolis.com/documento/dc_8bba00ffd81a

How to cite

GEM-KMeans: Memory-Efficient and Accurate Clustering on Massive Scale with GPU Optimization — arXiv:2609.36074 — arXiv (en), https://arxiv.org/abs/2609.36074 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8bba00ffd81a (Metraipolis archive dc_8bba00ffd81a, sha256 940b4dea22e824ee3aa56f049bcc91c87c87affc0d717b6f27bea3deb16ef35e)
BibTeX
@misc{dc8bba00ffd81a,
  title = {GEM-KMeans: Memory-Efficient and Accurate Clustering on Massive Scale with GPU Optimization — arXiv:2609.36074},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36074},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8bba00ffd81a; sha256 940b4dea22e824ee3aa56f049bcc91c87c87affc0d717b6f27bea3deb16ef35e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36074. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Memory-efficient scaling on clustering problems without sacrificing statistical accuracy is of central interest for large-scale data analysis and machine learning problems. Nonnegative low-rank (NLR) matrix factorization for $K$-means is a scalable clustering method, which connects to semidefinite relaxations with optimal average-case exact recovery guarantees. However, a direct GPU implementation of NLR requires multiple large factor-sized buffers and substantial data movements that are essentially memory-bound. In this paper, we introduce GEM-KMeans, a spectrally normalized yet mathematically equivalent NLR formulation that fuses the gradient update, nonnegative projection, and sufficient statistics for normalization and iterate movement into a matrix-multiplication epilogue. Instead of retaining three massive factor-sized arrays, our IO-aware GPU implementation materializes only one single factor with small tile-reduction arrays as additional storage in the High Bandwidth Memory (HBM). We derive explicit memory costs and spectrally normalized smoothness bounds for optimizing the clustering objective function. Accurate clustering is demonstrated at massive scales on synthetic and real datasets, where performance gains of GEM-KMeans over existing GPU-accelerated Lloyd's algorithms involve data-dependent runtime tradeoffs.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AR).
Categorie arXiv: Machine Learning (cs.LG) ; Hardware Architecture (cs.AR); Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2609.36074 — 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 2026-10-07T16:31:49.775Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).