%0 Generic %1 zhao2024galore %A Zhao, Jiawei %A Zhang, Zhenyu %A Chen, Beidi %A Wang, Zhangyang %A Anandkumar, Anima %A Tian, Yuandong %D 2024 %K cs.LG %T GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

@misc{zhao2024galore, added-at = {2024-03-13T07:26:13.000+0100}, archiveprefix = {arXiv}, author = {Zhao, Jiawei and Zhang, Zhenyu and Chen, Beidi and Wang, Zhangyang and Anandkumar, Anima and Tian, Yuandong}, biburl = {https://www.bibsonomy.org/bibtex/2bfbc4c8015bbceb1280063b1270bb982/aerover}, description = {GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection}, eprint = {2403.03507}, interhash = {3a4d0113d27e5fbec868e2b49dcb8086}, intrahash = {bfbc4c8015bbceb1280063b1270bb982}, keywords = {cs.LG}, primaryclass = {cs.LG}, timestamp = {2024-03-13T07:26:13.000+0100}, title = {GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection}, year = 2024 }