ICML 2024 "variance reduction techniques" Papers
3 papers found
Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient
Hao Di, Haishan Ye, Yueling Zhang et al.
ICML 2024spotlight
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang et al.
ICML 2024poster
Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models
Tanmay Gautam, Youngsuk Park, Hao Zhou et al.
ICML 2024poster