LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression

[2607.03057] LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2607.03057 (cs) [Submitted on 3 Jul 2026 ( v1 ), last revised 15 Aug 2026 (this version, v2)] Title: LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression Authors: Zhuowen Liu , Longkun Hao , Shiyu Feng , Xiaowen Chang , Ruiqun Li , Changqun Li View a PDF of the paper titled LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression, by Zhuowen Liu and 5 other authors View PDF HTML (experimental) Abstract: The rapid growth in the parameter scale of large language models (LLMs) has created a strong demand for efficient compression techniques. As a hardware-agnostic and highly compatible approach, low-rank compression has been widely adopted to reduce both memory footprint and computational cost. However, existing SVD-based methods are still largely driven by local reconstruction objectives, overlooking two critical limitations: rank budgets are often allocated without explicitly considering layer-wise loss sensitivity, and local approximation errors can propagate and accumulate through the residual stream, leading to amplified global deviations from the original model. To address these issues, we propose LACE-SVD, a Loss-Aware SVD framework with Cumulative Error correction for LLM compression. LACE-SVD first estimates the calibration negative-log-likelihood increase induced by candidate layer-wise compression ratios and solves a budget-constrained allocation problem to assign rank budgets. It then refines the compressed model with closed-form local updates and introduces a propagation-aware correction for residual-stream output modules, reducing layer-output discrepancy as a proxy for cumulative error propagation. Experimental results demonstrate that at a high compression ratio (0.6), the WikiText-2 PPL of our method on LLaMA-7B (32.57) is significantly better than that of Dobi-SVD (46.18). Comments: 12 pages, 5 figures, 5 tables Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2607.03057 [cs.LG] (or arXiv:2607.03057v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2607.03057 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhuowen Liu [ view email ] [v1] Fri, 3 Jul 2026 07:46:13 UTC (1,098 KB) [v2] Sat, 15 Aug 2026 08:33:27 UTC (1,098 KB) Full-text links: Access Paper: View a PDF of the paper titled LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression, by Zhuowen Liu and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-07 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• LACE-SVD: Loss-Aware SVD with Cumulative Error Correction for LLM Compression#608922
• Mind the Approximation: Fisher-Weighted SVD Compression for ViTs#975211
• Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy#1035008
• An error bound-based convergence analysis framework for a class of randomized algorithms#798805
• An error bound-based convergence analysis framework for a class of randomized algorithms#797391