Quanquan Gu

I am an Associate Professor of Computer Science at UCLA. I am leading the UCLA Artificial General Intelligence Lab. I received my Ph.D. degree in Computer Science from the University of Illinois at Urbana-Champaign in 2014. My research is in artificial intelligence and machine learning, with a focus on nonconvex optimization, deep learning, reinforcement learning, Large Language Models (LLMs), and deep generative models (e.g., diffusion models). Recently, I have been utilizing AI to enhance scientific discovery in domains such as biology, medicine, chemistry, and public health.

Here is my latest CV.

News and Annoucement

• [Nov 28, 2023] We are oragnizing the New Frontiers of AI for Drug Discovery and Development at NeurIPS 2023.

Recent Research Highlight

• Self-Play Preference Optimization for Language Model Alignment
  Yue Wu*, Zhiqing Sun*, Huizhuo Yuan*, Kaixuan Ji, Yiming Yang and Quanquan Gu, arXiv:2405.00675, 2024.

• Self-Play Fine-Tuning of Diffusion Models for Text-to-Image Generation
  Huizhuo Yuan*, Zixiang Chen*, Kaixuan Ji* and Quanquan Gu, arXiv:2402.10210, 2024.

• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
  Zixiang Chen*, Yihe Deng*, Huizhuo Yuan*, Kaixuan Ji and Quanquan Gu, in Proc. of the 41th International Conference on Machine Learning (ICML), Vienna, Austria, 2024. [arXiv]

• Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
  Yiwen Kou*, Zixiang Chen* and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 36, New Orleans, LA, USA, 2023. [arXiv]

• 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. [arXiv]

• Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes
  Jiafan He, Heyang Zhao, Dongruo Zhou and Quanquan Gu, in Proc. of the 40th International Conference on Machine Learning (ICML), Hawaii, USA, 2023. [arXiv]

• Benign Overfitting for Two-layer ReLU Convolutional Neural 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. [arXiv]

• Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency
  Heyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang and Quanquan Gu, in Proc. of the 36th Annual Conference on Learning Theory (COLT), Bangalore, India, 2023. [arXiv]

• Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs
  Dongruo Zhou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. Oral Presentation [arXiv]

• Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions
  Jiafan He, Dongruo Zhou, Tong Zhang and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

• Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime
  Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. [arXiv]

• Benign Overfitting in Two-layer Convolutional Neural Networks
  Yuan Cao*, Zixiang Chen*, Mikhail Belkin and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 35, New Orleans, LA, USA, 2022. Oral Presentation [arXiv]

• Last Iterate Risk Bounds of SGD with Decaying Stepsize for Overparameterized Linear Regression
  Jingfeng Wu*, Difan Zou*, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of the 39th International Conference on Machine Learning (ICML), Baltimore, MD, USA, 2022. Long presentation [arXiv]

• The Benefits of Implicit Regularization from SGD in Least Squares Problems
  Difan Zou*, Jingfeng Wu*, Vladimir Braverman, Quanquan Gu, Dean P. Foster and Sham M. Kakade, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

• Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures
  Yuan Cao, Quanquan Gu, Mikhail Belkin, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 34, 2021. [arXiv]

• Benign Overfitting of Constant-Stepsize SGD for Linear Regression
  Difan Zou, Jingfeng Wu, Vladimir Braverman, Quanquan Gu and Sham M. Kakade, in Proc. of the 34th Annual Conference on Learning Theory (COLT), 2021. [arXiv]

• Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
  Dongruo Zhou, Quanquan Gu and Csaba Szepesvári, in Proc. of the 34th Annual Conference on Learning Theory (COLT), 2021. [arXiv]

• Agnostic Learning of Halfspaces with Gradient Descent via Soft Margins
  Spencer Frei, Yuan Cao and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. Long talk [arXiv]

• Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping
  Dongruo Zhou, Jiafan He and Quanquan Gu, in Proc. of the 38th International Conference on Machine Learning (ICML), 2021. [arXiv]

• 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. [arXiv]

• A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks
  Zixiang Chen, Yuan Cao, Quanquan Gu and Tong Zhang, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 33, 2020. [arXiv]

• Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
  Yuan Cao and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019. Spotlight presentation [arXiv]

• An Improved Analysis of Training Over-parameterized Deep Neural Networks
  Difan Zou and Quanquan Gu, in Proc. of Advances in Neural Information Processing Systems (NeurIPS) 32, Vancouver, Canada, 2019. [arXiv]

• Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
  Difan Zou*, Yuan Cao*, Dongruo Zhou and Quanquan Gu, Accepted by the Machine Learning Journal (MLJ), 2019. [arXiv]

• Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
  Dongruo Zhou and Quanquan Gu, in Proc. of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA, 2019. [arXiv]

• Stochastic Nested Variance Reduction for Nonconvex Optimization
  Dongruo Zhou, Pan Xu and Quanquan Gu, In Proc. of Advances in Neural Information Processing Systems (NeurIPS) 31, Montréal, Canada, 2018. Spotlight presentation [arXiv]

Recent Services

• Senior Area Chair for NeurIPS 2023, Area Chair for ICLR 2024, AISTATS 2024, AAAI 2024

Awards

• WSDM Test of Time Paper Award, 2024

• Alfred P. Sloan Research Fellowship, 2022

• JP Morgan Faculty Research Award, 2022

• IJCAI Early Career Spotlight, 2020

• AWS Machine Learning Research Award, 2019

• Simons Berkeley Research Fellowship, 2019

• Adobe Data Science Research Award, 2018

• Salesforce Deep Learning Research Award, 2018

• NSF CAREER Award, 2017

• Yahoo! Academic Career Enhancement Award, 2015

Contact

• Address: EVI 382, 404 Westwood Plaza, Los Angeles, CA 90095

• Email: qgu at cs dot ucla dot edu

Tweets by QuanquanGu