LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Yuanhe Zhang; Fanghui Liu; Yudong Chen

2025 ICML ICML 2025

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Yuanhe Zhang, Fanghui Liu, Yudong Chen

Topics

Machine Learning > Optimization & Theory > Optimization Machine Learning > Learning Types > Transfer Learning Artificial Intelligence > Core AI > Large Language Models

Keywords

gradient descent linear convergence generalization low-rank adaptation singular subspace preconditioners

Download PDF