Quanquan Gu

I am an Associate Professor of Computer Science at UCLA. I am leading the Statistical Machine Learning Lab. I received my Ph.D. degree in Computer Science from the University of Illinois at Urbana-Champaign in 2014. My research is in machine learning, with a focus on developing and analyzing nonconvex optimization algorithms for machine learning to understand large-scale, dynamic, complex, and multi-modal data, and build the foundations of deep learning and reinforcement learning. Recently, I use AI to develop next-generation database management systems and empower scientific discovery in domains such as biology, medicine, chemistry, and public health.

Here is my latest CV.

News and Annoucement

• [July 30, 2022] We are oragnizing a workshop on representation learning theory at TTIC on August 4-5, 2022.

• [July 30, 2022] We are oragnizing the Optimization for Machine Learning Workshop at NeurIPS 2022.

Recent Research Highlight

• 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

• Area Chair for ICLR 2023, AISTATS 2023, AAAI 2023

Awards

• 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

• Follow @QuanquanGu

Tweets by QuanquanGu