Zeyuan Allen-Zhu

LoRA: Low-Rank Adaptation of Large Language Models

J. Edward Hu, Yelong Shen, Phillip Wallis et al. · arXiv (Cornell University) · 2021 · 2.4K citations · Full text

Llm Fine-tuning, Engineering, Machine Learning +19

A Convergence Theory for Deep Learning via Over-Parameterization

Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song · arXiv (Cornell University) · 2018 · 626 citations · Full text

Artificial Intelligence, Deep Neural Networks, Engineering +13

Is Q-learning Provably Efficient?

Chi Jin, Zeyuan Allen-Zhu, Sébastien Bubeck et al. · arXiv (Cornell University) · 2018 · 337 citations · Full text

Artificial Intelligence, Ucb Exploration, Engineering +18

A Convergence Theory for Deep Learning via Over-Parameterization

Zeyuan Allen-Zhu, Yuanzhi Li, Zhao Song · International Conference on Machine Learning · 2018 · 175 citations

Artificial Intelligence, Convolutional Neural Network, Engineering +16

Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

Zeyuan Allen-Zhu, Yuanzhi Li, Yingyu Liang · arXiv (Cornell University) · 2018 · 172 citations · Full text

Artificial Intelligence, Neural Scaling Law, Hyperparameter Estimation +15