A Feature-Major Codebook for Memory-Efficient Sparse-Binary Self-Organizing Maps: Scaling a MEDLINE Atlas to 1.05 Million Neurons on a Single Consumer GPU

arXiv:2608.24067 · cs.LG, cs.DC · Submitted 2026-08-25 · Read on arXiv

cs.LG, cs.DC

Submitted: 2026-08-25

Updated: 2026-09-02

Comments: 41 pages, 11 tables, 7 figures. v2 applies seven corrections narrowing statements later measurement scoped, adds a section on a post-submission symmetric tuning programme, and carries that addendum and a corrigendum as ancillary files. No published number is withdrawn. Code and frozen results: doi:10.5281/zenodo.22245649 (tag v1.1). Corpus: doi:10.5281/zenodo.20770707. Addendum DOIs in Sec. 8

Code: https://github.com/mongrolwarrior/sparsesom-roofline-addendum

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

Terminology

• Clustering — 3× in this paper · explained in 2 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Provenance — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Kernel decomposition — 2× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Paper Review — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

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