SOURCE-LINKED INTELLIGENCE

Structured Transforms for Low-Overhead Quantization of Language Models

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

We revisit Kashin-decomposition-based weight quantization for large language models and propose an improved algorithm with stronger convergence properties and structured, efficient orthogonal transforms. The method retains the core factorization of each weight into two components -- one with bounded infinity norm and the other with bounded infinity norm after an orthogonal transformation -- but replaces the dense random orthogonal matrix with a sign-randomized Discrete Cosine Transform (DCT), reducing the per-iteration cost from $\mathcal{O}(N^2)$ to $\mathcal{O}(N \log N)$. The proposed greed

Read original source ↗ Open in workspace

recordType

paper

region

Global