Quanquan Gu
I am an Assistant Professor of Computer Science at UCLA. My research is in statistical machine learning, with a focus on developing robust, adaptive and efficient machine learning, data mining and optimization algorithms with provable guarantee to understand large-scale, dynamic, complex and heterogeneous data in social and information networks, neuroscience and genomics. I am leading the Statistical Machine Learning Lab. Before I joined UCLA, I have worked as an Assistant Professor at the University of Virginia for more than three years, and was a Postdoctoral Research Associate at Princeton University. I received my Ph.D. degree in Computer Science from the University of Illinois at Urbana-Champaign in 2014.
I am very fortunate to have received a couple of awards for my work, including Simons Berkeley Research Fellowship in 2019, Salesforce Deep Learning Research Award and Adobe Data Science Research Award in 2018, NSF CAREER Award in 2017, and Yahoo! Academic Career Enhancement Award in 2015. Here is my latest CV.
News and Annoucement
- [11/2/2018] I gave a talk on "Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks: Algorithms and Theory" at USC ISI AI Seminar.
- [11/8/2018] I gave a talk on "New Variance Reduction Algorithms for Nonconvex Finite-Sum Optimization" at USC Machine Learning Seminar.
For Prospective Students
I am actively looking for talented graduate and undergraduate students interested in theory of deep learning, adversarial machine learning, nonconvex optimization, reinforcement learning and their applications joining my lab. Please indicate your interest in working with me in your application. Due to time and lab space limit, I don't host visiting students or summer interns.Recent Research Highlight
-
A Generalization Theory of Gradient Descent for Learning Over-parameterized Deep ReLU Networks
Yuan Cao and Quanquan Gu, arXiv:1902.01384, 2019. -
Stochastic Recursive Variance-Reduced Cubic Regularization Methods
Dongruo Zhou and Quanquan Gu, arXiv:1901.11518, 2019. -
Lower Bounds for Smooth Nonconvex Finite-Sum Optimization
Dongruo Zhou and Quanquan Gu, arXiv:1901.11224, 2019. -
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks
Difan Zou*, Yuan Cao*, Dongruo Zhou and Quanquan Gu, arXiv:1811.08888, 2018. -
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 [arXiv] -
On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization
Dongruo Zhou*, Yiqi Tang*, Ziyan Yang*, Yuan Cao and Quanquan Gu, arXiv:1808.05671, 2018.
Contact
Address: EVI 282, 404 Westwood Plaza, Los Angeles, CA 90095
Email: qgu at cs dot ucla dot edu
Follow @QuanquanGu