ConMeZO accelerates zeroth-order optimization for LLM finetuning by restricting random direction sampling to a momentum-centered cone, matching MeZO's worst-case rate but showing 2X empirical speedup.
Section C.4 explores their roles in convergence acceleration and alignment with the true gradient, highlighting key patterns observed in the experiments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ConMeZO: Adaptive Descent-Direction Sampling for Gradient-Free Finetuning of Large Language Models
ConMeZO accelerates zeroth-order optimization for LLM finetuning by restricting random direction sampling to a momentum-centered cone, matching MeZO's worst-case rate but showing 2X empirical speedup.