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

GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning 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 perturbation per mini-batch example and aggregates the per-example losses th