Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models

Created by W.Langdon from gp-bibliography.bib Revision:1.9085

@InProceedings{pmlr-v235-dong24b,

• author = "Peijie Dong and Lujun Li and Zhenheng Tang and Xiang Liu and Xinglin Pan and Qiang Wang2 and Xiaowen Chu",
• title = "Pruner-Zero: Evolving Symbolic Pruning Metric From Scratch for Large Language Models",
• booktitle = "Proceedings of the 41st International Conference on Machine Learning",
• year = "2024",
• editor = "Ruslan Salakhutdinov and Zico Kolter and Katherine Heller and Adrian Weller and Nuria Oliver and Jonathan Scarlett and Felix Berkenkamp",
• volume = "235",
• series = "Proceedings of Machine Learning Research",
• pages = "11346--11374",
• address = "Seoul, South Korea",
• month = "21--27 " # jul,
• publisher = "PMLR",
• keywords = "genetic algorithms, genetic programming, LLM, ANN",
• URL = "https://icml.cc/virtual/2024/poster/35128",
• URL = "https://proceedings.mlr.press/v235/dong24b.html",
• URL = "https://raw.githubusercontent.com/mlresearch/v235/main/assets/dong24b/dong24b.pdf",
• code_url = "https://github.com/pprp/Pruner-Zero",
• size = "29 pages",
• abstract = "we develop an automatic framework for searching symbolic pruning metrics using genetic programming. Pruner-Zero allows auto-generation of symbolic pruning metrics. extensive experiments on LLaMA and LLaMA-2 on language modeling and zero-shot tasks demonstrate that our Pruner-Zero obtains superior performance",
• notes = "ICML 2026 https://icml.cc/virtual/2026",

}

Genetic Programming entries for Peijie Dong Lujun Li Zhenheng Tang Xiang Liu Xinglin Pan Qiang Wang2 Xiaowen Chu

Citations