@article{platonpruninglargetransformermodelswith, title = {PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance}, author = {Qingru Zhang and Simiao Zuo and Chen Liang and Alexander Bukharin and Pengcheng He and Weizhu Chen and Tuo Zhao}, year = {2022}, eprint = {2206.12562}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2206.12562v1}, }