GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning

Liyan Tan, Yequan Zhao, Yifan Yang, Ruijie Zhang, Xinling Yu, Zheng Zhang

Jun 3, 2026 at 04:00

10 Views

0 Comments

arXiv:2606.02857v1 Announce Type: cross Abstract: Zeroth-order (ZO) optimization is a memory-efficient alternative to backpropagation for fine-tuning large language models, but its deployment is limited by the high variance of gradient estimation. We propose GRZO, a Group-Relative Zeroth-Order optimizer that draws one pseudo-independent...

Read the full article at the source.

Read Original Article

Was this helpful?