AI RESEARCH
ERC-SVD: Error-Controlled SVD for Large Language Model Compression
arXiv CS.AI
•
ArXi:2505.20112v4 Announce Type: replace-cross Large language models (LLMs) have nstrated impressive capabilities in a wide range of downstream natural language processing tasks. Nevertheless, their considerable sizes and memory demands hinder practical deployment, underscoring the importance of developing efficient compression strategies. Singular value decomposition (SVD) decomposes a matrix into orthogonal components, enabling efficient low-rank approximation. This is particularly suitable for LLM compression, where weight matrices often exhibit significant redundancy.