Bio

B.S. ​Tsinghua University, 2007M.S. ​​Tsinghua University, 2010Ph.D. ​University of Illinois at Urbana-Champaign, 2014Post-Doc ​Princeton University, 2015

"It is never too late to be what you might have been."

George Eliot

Quanquan Gu was an Assistant Professor in the Department of Computer Science at the University of Virginia and now holds a courtesy appointment. Prior to joining the University of Virginia, Dr. Gu was a Postdoctoral Research Associate in the Department of Operations Research and Financial Engineering at Princeton University. He received IBM Ph.D. Fellowship in 2013 when he was pursuing his Ph.D. degree in the Department of Computer Science, University of Illinois at Urbana-Champaign. His current research focuses on Machine Learning, High-dimensional Statistical Inference, Data Mining and Optimization.

Awards

  • NSF CAREER Award 2017
  • Yahoo! Academic Career Enhancement Award 2015

Research Interests

  • Machine Learning
  • Data Mining
  • Optimization
  • High-dimensional Statistics

Selected Publications

  • On the Statistical Limits of Convex Relaxations: A Case Study. In Proc. of the 33th International Conference on Machine Learning (ICML), New York, USA. 2016. Zhaoran Wang and Quanquan Gu and Han Liu.
  • Towards Faster Rates and Oracle Property for Low-Rank Matrix Estimation. In Proc. of the 33th International Conference on Machine Learning (ICML), New York, USA. 2016. Huan Gui and Jiawei Han and Quanquan Gu
  • Semiparametric Differential Graph Models, In Proc. of Advances in Neural Information Processing Systems (NIPS) 29, Barcelona, Spain. 2016. Pan Xu and Quanquan Gu.
  • Accelerated Stochastic Block Coordinate Descent with Optimal Sampling, in Proc of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA. 2016. Aston Zhang and Quanquan Gu.
  • Towards a Lower Sample Complexity for Robust One-bit Compressed Sensing. In Proc. of the 32nd International Conference on Machine Learning (ICML'15), Lille, France. 2015. Rongda Zhu and Quanquan Gu.
  • High Dimensional Expectation-Maximization Algorithm: Statistical Optimization and Asymptotic Normality. In Proc. of Advances in Neural Information Processing Systems (NIPS) 28, Montreal, Quebec, Canada, 2015. Zhaoran Wang, Quanquan Gu, Yang Ning, and Han Liu.
  • Sparse PCA with Oracle Property. in Proc. of Advances in Neural Information Processing Systems (NIPS’14) 27, Montreal, Quebec, Canada. 2014. Quanquan Gu, Zhaoran Wang, Han Liu.
  • Robust Tensor Decomposition with Gross Corruption. in Proc. of Advances in Neural Information Processing Systems (NIPS’14) 27, Montreal, Quebec, Canada. 2014. Quanquan Gu, Huan Gui, Jiawei Han.
  • Selective Sampling on Graphs for Classification. in Proc. of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’13), Chicago, USA, pp.131-139. 2013. Quanquan Gu, Charu Aggarwal, Jialu Liu, Jiawei Han.
  • Selective Labeling via Error Bound Minimization. in Proc. of Advances in Neural Information Processing Systems (NIPS’12) 25, Lake Tahoe, Nevada, United States, pp.332-340. 2012. Quanquan Gu, Tong Zhang, Chris Ding, Jiawei Han.
  • Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017. Aditya Chaudhry, Pan Xu and Quanquan Gu.
  • Variance-Reduced Stochastic Gradient High-dimensional Expectation-Maximization Algorithm, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017. Rongda Zhu, Lingxiao Wang, Chengxiang Zhai, Quanquan Gu.
  • A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017. Lingxiao Wang* and Xiao Zhang* and Quanquan Gu,
  • Robust Gaussian Graphical Model Estimation with Arbitrary Corruption, in Proc. of the 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017. Lingxiao Wang, Quanquan Gu.
  • Fast Newton Hard Thresholding Pursuit for Sparsity Constrained Nonconvex Optimization, in Proc of the 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Halifax, Nova Scotia, Canada, 2017. Jinghui Chen and Quanquan Gu.

Courses Taught

  • SYS 6016/4582 Machine Learning Spring 2017
  • CS6501/SYS 6003 Optimization for Machine Learning Fall 2015, 2016, 2017
  • SYS 3060 Introduction to Reinforcement Learning Spring 2016