ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
arXiv:2511.02757v2 Announce Type: replace-cross
Abstract: Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the memory overhead of backpropagation. However, …