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

arXiv:2609.36074 · cs.LG, cs.AR, cs.PF · Submitted 2026-09-28 · Read on arXiv

cs.LG, cs.AR, cs.PF

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/AnswerDotAI/fastkmeans

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Clustering — 1× in this paper · explained in 2 episodes

Sources

• SemDeDup: Data-efficient learning at web-scale through semantic deduplication
• Statistical and Computational Guarantees of Lloyd's Algorithm and its Variants
• Flash-KMeans: Fast and Memory-Efficient Exact K-Means

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks