English(EN) OPTIMA: Optimal One-shot Pruning for LLMs via Quadratic Programming Reconstruction

OPTIMA方法通过二次规划提供高效的LLM剪枝

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

研究人员开发了OPTIMA，一种新颖的大型语言模型（LLM）单次剪枝方法，可在准确性和计算可行性之间取得平衡。该方法将层级权重重建构建为独立的、逐列的二次规划问题，这些问题可以高效地批量处理并在加速器上求解。OPTIMA在LLaMA和Gemma模型的各种稀疏度水平上均展现出改进的零样本准确率，其性能优于启发式方法，同时在各自的掩码上可与精确重建技术相媲美。 AI

影响通过在不显著损失准确率的情况下降低推理成本，从而实现更高效的LLM部署。

排序理由关于LLM剪枝新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于LLM剪枝新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 3 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Mohammad Mozaffari, Samuel Kushnir, Maryam Mehri Dehnavi, Amir Yazdanbakhsh · 2026-10-21 04:00

OPTIMA：通过二次规划重建实现LLM的最佳单次剪枝

arXiv:2512.13886v3 Announce Type: replace-cross Abstract: Post-training pruning cuts the inference cost of large language models, yet it faces a trade-off: simple heuristics that zero weights are fast but degrade accuracy, while principled joint optimization methods recover accur…

本文如何被排名

报道来源 [1]

OPTIMA：通过二次规划重建实现LLM的最佳单次剪枝

相关实体

相关话题