Xingguo Li — Publications

Deep Learning

• “Deep Hyperspherical Learning” [slide]
  Weiyang Liu, Yan-Ming Zhang, Xingguo Li, Zhiding Yu, Bo Dai, Tuo Zhao, and Le Song
  Neural Information Processing Systems (NIPS), 2017  (*Spotlight*)
  

• “On Computation and Generalization of Generative Adversarial Imitation Learning”
  Minshuo Chen, Yizhou Wang, Tianyi Liu, Xingguo Li, Zhuoran Yang, Zhaoran Wang, and Tuo Zhao
  NeurIPS Optimization Foundations for Reinforcement Learning Workshop, 2019  (*Spotlight*)
  

• “On Tighter Generalization Bound for Deep Neural Networks: CNNs, ResNets, and Beyond”
  Xingguo Li, Junwei Lu, Zhaoran Wang, Jarvis Haupt, and Tuo Zhao (Preprint)
  

• “On Generalization Bounds of a Family of Recurrent Neural Networks”
  Minshuo Chen, Xingguo Li, and Tuo Zhao (submitted)
  

• “Can Increasing Network Size Improve Generalization?”
  Xingguo Li and Tuo Zhao (Preprint)
  

Statistical Learning & Optimization

• “Symmetry, Saddle Points, and Global Geometry of Nonconvex Matrix Factorization” [slide]
  Xingguo Li, Zhaoran Wang, Junwei Lu, Raman Arora, Jarvis Haupt, Han Liu, and Tuo Zhao
  IEEE Transactions on Information Theory (TIT), vol. 65, no. 6, pp. 3489 - 3514, 2019
  

• “ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization”
  Xiangyi Chen, Sijia Liu, Kaidi Xu, Xingguo Li, Due Lin, Mingyi Hong, and David Cox
  Neural Information Processing Systems (NeurIPS), 2019
  

• “On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don't Worry About its Nonsmooth Loss Function.”
  Xingguo Li, Haoming Jiang, Jarvis Haupt, Raman Arora, Han Liu, Mingyi Hong, and Tuo Zhao
  Conference on Uncertainty in Artificial Intelligence (UAI), 2019
  

• “NOODL: Provable Online Dictionary Learning and Sparse Coding”
  Sirisha Rambhatla, Xingguo Li, and Jarvis Haupt
  International Conference on Learning Representations (ICLR), 2019

• “On Constrained Nonconvex Stochastic Optimization: A Case Study for Generalized Eigenvalue Decomposition”
  Zhehui Chen, Xingguo Li, Lin Yang, Jarvis Haupt, and Tuo Zhao
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
  

• “Towards Black-box Iterative Machine Teaching”
  Weiyang Liu, Bo Dai, Xingguo Li, Zhen Liu, James Rehg, and Le Song
  International Conference on Machine Learning (ICML), 2018
  

• “On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization”
  Xingguo Li, Tuo Zhao, Raman Arora, Han Liu, and Mingyi Hong
  Journal of Machine Learning Research (JLMR), vol. 18, no. 184, pp. 1 - 24, 2018
  

• “Zeroth-Order Stochastic Projected Gradient Descent for Nonconvex Optimization”
  Sijia Liu, Xingguo Li, Pin-Yu Chen, Jarvis Haupt, and Lisa Amini
  IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2018
  

• “On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning”
  Xingguo Li, Lin Yang, Jian Ge, Jarvis Haupt, Tong Zhang, and Tuo Zhao
  Neural Information Processing Systems (NIPS), 2017 (short version)
  

• “Target Based Hyperspectral Demixing via Generalized Robust PCA”
  Sirisha Rambhatla, Xingguo Li, and Jarvis Haupt
  Asilomar Conference on Signals, Systems, and Computers (Asilomar), 2017
  (*Best Student Paper Award Finalist*)
  

• “Communication-Efficient Distributed Optimization for Sparse Learning via Two-Way Truncation”
  Jineng Ren, Xingguo Li and Jarvis Haupt
  IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2017
  

• “Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning” [slide]
  Xingguo Li, Tuo Zhao, Raman Arora, Han Liu, and Jarvis Haupt
  International Conference on Machine Learning (ICML), 2016
  

• “An Improved Convergence Analysis of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization”
  Xingguo Li*, Tuo Zhao*, Raman Arora, Han Liu, and Mingyi Hong
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2016
  

• “Provable Online CP/PARAFAC Decomposition of a Structured Tensor via Dictionary Learning”
  Sirisha Rambhatla, Xingguo Li, and Jarvis Haupt  (Submitted)
  

• “Nonconvex Sparse Learning via Stochastic Optimization with Progressive Variance Reduction”
  Xingguo Li, Tuo Zhao, Raman Arora, Han Liu, and Jarvis Haupt
  IEEE Transactions on Information Theory (TIT)  (Revision)
  

• “Statistical and Computational Tradeoffs of Regularized Dantzig-type Estimator”
  Xingguo Li, Yanbo Xu, Tuo Zhao, and Han Liu
  Electronic Journal of Statistics (EJS)  (Revision)
  

Data Sketching & Robust PCA

• “Sketching Dictionary Based Robust PCA in Large Matrices”
  Xingguo Li and Jarvis Haupt
  Asilomar Conference on Signals, Systems, and Computers (Asilomar), 2019
  

• “Robust PCA via Dictionary Based Outlier Pursuit”
  Xingguo Li, Jineng Ren, Sirisha Rambhatla, YangYang Xu, and Jarvis Haupt
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
  

• “Near Optimal Sketching of Low-Rank Tensor Regression”
  Xingguo Li, Jarvis Haupt, and David Woodruff
  Neural Information Processing Systems (NIPS), 2017
  

• “Robust Outlier Identification for Noisy Data via Randomized Adaptive Compressive Sampling”
  Xingguo Li and Jarvis Haupt
  The Signal Processing with Adaptive Sparse Structured Representations Workshop (SPARS), 2017
  

• “Robust Low-Complexity Methods for Matrix Column Outlier Identification”
  Xingguo Li and Jarvis Haupt
  IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2017
  

• “A Dictionary Based Generalization of Robust PCA”
  Sirisha Rambhatla, Xingguo Li, and Jarvis Haupt
  IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2016
  

• “Robust PCA via Tensor Outlier Pursuit”
  Jineng Ren, Xingguo Li, and Jarvis Haupt
  Asilomar Conference on Signals, Systems, and Computers (Asilomar), 2016
  

• “A Refined Analysis for the Sample Complexity of Adaptive Compressive Outlier Sensing”
  Xingguo Li and Jarvis Haupt
  IEEE Workshop on Statistical Signal Processing (SSP), 2016
  

• “Identifying Outliers in Large Matrices via Randomized Adaptive Compressive Sampling” [slide]
  Xingguo Li and Jarvis Haupt
  IEEE Transactions on Signal Processing (TSP), vol. 63, no. 7, pp. 1792 - 1807, 2015
  

• “Locating Salient Group-Structured Image Features via Adaptive Compressive Sensing” [slide]
  Xingguo Li and Jarvis Haupt
  IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2015
  (*Best Student Paper Award*)
  

• “Outlier Identification via Randomized Adaptive Compressive Sampling”
  Xingguo Li and Jarvis Haupt
  40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015
  

• “A Dictionary-Based Generalization of Robust PCAwith Applications to Target Localization in Hyperspectral Imaging”
  Sirisha Rambhatla, Xingguo Li, Jineng Ren, and Jarvis Haupt
  IEEE Transactions on Signal Processing (TSP)  (Revision)
  

• “Robust Low-Complexity Randomized Methods for Locating Outliers in Large Matrices”
  Xingguo Li and Jarvis Haupt
  IEEE Transactions on Signal Processing (TSP)  (Revision)
  

Scalable Software

• “The flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R”
  Xingguo Li*, Tuo Zhao*, Lie Wang, Xiaoming Yuan, and Han Liu
  Journal of Machine Learning Research (JLMR), vol. 16, pp. 553 - 557, 2015
  

• “Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python” [vignette] [github]
  Xingguo Li*, Jian Ge*, Haoming Jiang, Han Liu, Tong Zhang, Mengdi Wang, and Tuo Zhao
  Journal of Machine Learning Research (JLMR), vol. 20, pp. 1 - 5, 2019
  (A package paper by Xingguo Li, Tong Zhang, Han Liu, and Tuo Zhao,
  received ASA *Best Student Paper Award * on Statistical Computing, 2016)
  

Other Publications

• “Structured Learning with Parsimony in Measurements and Computations: Theory, Algorithms, and Applications”
  Xingguo Li
  Ph.D. Dissertation, University of Minnesota Twin Cities, 2018
  

(*Co-first author)