Advancing SVD-based LLM Compression via Layer-Wise Error Model Search

Paper recorded by Signals 4 on 2026-10-23 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-23 on arXiv · recorded by Signals 4 on 2026-10-26

Category: cs.AI · 人工智能 · first seen 2026-10-26

Abstract

Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing methods face two key limitations: (i) global rank allocation, where uncalibrated error proxies fail to capture complex error propagation, and (ii) decomposition quality, where Fisher-based estimators suffer from severe rank collapse. In this work, we address these limitations by i

Read on arXiv →