Publications (* indicates equal contribution): 

• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Zixiang Chen*, Yihe Deng*, Huizhuo Yuan*, Kaixuan Ji and Quanquan Gu, arXiv:2401.01335, 2024.

• Fast Sampling via De-randomization for Discrete Diffusion Models

Zixiang Chen, Huizhuo Yuan, Yongqian Li, Junkai Zhang, Yiwen Kou, Quanquan Gu,

NeurIPS 2023 Workshop on Diffusion Models.

• Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves

Yihe Deng, Weitong Zhang, Zixiang Chen and Quanquan Gu, arXiv:2311.04205, 2023.

• Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP

Zixiang Chen*, Yihe Deng*, Yuanzhi Li, and Quanquan Gu, 

In Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024.

•  How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

 Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Peter L Bartlett 

 In Proc. of the 12th International Conference on Learning Representations (ICLR), Vienna, Austria, 2024. Spotlight Presentation

• Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks,

Yiwen Kou*, Zixiang Chen* and Quanquan Gu

In Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023.

•  Why Does Sharpness-Aware Minimization Generalize Better Than SGD?

Zixiang Chen*, Junkai Zhang*, Yiwen Kou, Xiangning Chen, Cho-Jui Hsieh and Quanquan Gu

In Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023.

• Benign Overfitting for Two-layer ReLU Networks,

Yiwen Kou*, Zixiang Chen*, Yuanzhou Chen and Quanquan Gu,

In Proc. of the 40 th International Conference on Machine Learning (ICML), Hawaii, USA, 2023.

• Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron,

Jingfeng Wu*, Difan Zou*, Zixiang Chen*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade,

In Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023.

• A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning,

    Zixiang Chen*, Chris Junchi Li*, Huizhuo Yuan*, Quanquan Gu, Michael Jordan,

    In Proc. of the 11th International Conference on Learning Representations (ICLR), 2023. (Spotlight)

• How Does Semi-supervised learning with Pseudo-labelers Work? A Case Study,

Yiwen Kou, Zixiang Chen, Yuan Cao and Quanquan Gu,

     In Proc. of the 11th International Conference on Learning Representations (ICLR), 2023.

•  Understanding Train-Validation Split in Meta-Learning with Neural Networks,

 Xinzhe Zuo, Zixiang Chen, Huaxiu Yao, Yuan Cao and Quanquan Gu,

 In Proc. of the 10th International Conference on Learning Representations (ICLR), 2023.

•  Towards Understanding Mixture of Experts in Deep Learning,

 Zixiang Chen, Yihe Deng, Yue Wu, Quanquan Gu, Yuanzhi Li,

      Advances in Neural Information Processing Systems (NeurIPS) 36, 2022. 

• Benign Overfitting in Two-layer Convolutional Neural Networks,

Yuan Cao*, Zixiang Chen*, Mikhail Belkin, Quanquan Gu,

Advances in Neural Information Processing Systems (NeurIPS) 36, 2022 (Oral). 

• Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games,

Zixiang Chen, Dongruo Zhou and Quanquan Gu, 

In Proc. of the 33rd International Conference on Algorithmic Learning Theory (ALT), 2022.

•  Faster Perturbed Stochastic Gradient Methods for Finding Local Minima, 

Zixiang Chen*, Dongruo Zhou* and Quanquan Gu, 

In Proc. of the 33rd International Conference on Algorithmic Learning Theory (ALT), 2022.

• Self-training Converts Weak Learners to Strong Learners in Mixture Models,

Spencer Frei*, Difan Zou*, Zixiang Chen* and Quanquan Gu, 

In Proc of the 23rd International Conference on Artificial Intelligence and Statistics, 2022.

• How Much Over-parameterization Is Sufficient to Learn Deep ReLU Networks?

     Zixiang Chen*, Yuan Cao*, Difan Zou* and Quanquan Gu,

In Proc. of the 9th International Conference on Learning Representations (ICLR), 2021.

•  A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks,

 Zixiang Chen, Yuan Cao, Quanquan Gu and Tong Zhang,

 Advances in Neural Information Processing Systems (NeurIPS) 34, 2020. 

•  Stein Neural Sampler,

 Tianyang Hu*, Zixiang Chen*, Hanxi Sun*, Jincheng Bai, Mao Ye, Guang Cheng.