Yudong Chen -- Publications by topic

Reinforcement learning | Robust distributed learning | Non-convex optimization | Mixture of linear regressions | Graph clustering & community detection | Low-rank matrix/tensor estimation | Sparse & robust regresson | Wireless networks, signal processing & kernel methods | Intelligent transportation systems


Reinforcement learning

Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret
Yingjie Fei, Zhuoran Yang, Yudong Chen, Zhaoran Wang, and Qiaomin Xie
Neural Information Processing Systems Conference (NeurIPS), 2020. (Spotlight) [arxiv]

Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium
Qiaomin Xie, Yudong Chen, Zhaoran Wang, and Zhuoran Yang
Conference on Learning Theory (COLT), 2020. [arxiv]


Robust distributed learning and optimization


Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
Dong Yin, Yudong Chen, Kannan Ramchandran, and Peter Bartlett.
International Conference on Machine Learning (ICML), 2019 (long talk). [arxiv]

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
Dong Yin, Yudong Chen, Kannan Ramchandran, and Peter Bartlett.
International Conference on Machine Learning (ICML), 2018. [arxiv]


Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent
Yudong Chen, Lili Su, and Jiaming Xu.
ACM SIGMETRICS, 2018. [paper link] [arxiv]



Non-convex optimization for machine learning and statistics


Likelihood Landscape and Local Minima Structures of Gaussian Mixture Models
Yudong Chen and Xumei Xi
Preprint, 2020. [arxiv]

Structures of Spurious Local Minima in k-means
Wei Qian, Yuqian Zhang, and Yudong Chen
Preprint, 2020. [arxiv]

Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities
Wei Qian, Yuqian Zhang, and Yudong Chen.
Neural Information Processing Systems Conference (NeurIPS), 2019. [arxiv]

Factor Group-Sparse Regularization for Efficient Low-Rank Matrix Recovery
Jicong Fan, Lijun Ding, Yudong Chen, and Madeleine Udell
Neural Information Processing Systems Conference (NeurIPS), 2019. [arxiv]

Low-rank Matrix Recovery with Composite Optimization: Good Conditioning and Rapid Convergence
Vasileios Charisopoulos, Yudong Chen, Damek Davis, Mateo Diaz, Lijun Ding, and Dmitriy Drusvyatskiy.
Foundations of Computational Mathematics, to appear, 2019. [arxiv]

The Leave-one-out Approach for Matrix Completion: Primal and Dual Analysis
Lijun Ding and Yudong Chen.
IEEE Transactions on Information Theory, 2019. [arxiv] [ieee link]

Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation
Yudong Chen and Yuejie Chi.
IEEE Signal Processing Magazine, vol. 35, no. 4, pp. 14-31, 2018. [arxiv] [ieee link]

Fast Algorithms for Robust PCA via Gradient Descent
Xinyang Yi, Dohyung Park, Yudong Chen, and Constantine Caramanis.
Neural Information Processing Systems Conference (NIPS), 2016. [arxiv] [code]

Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees
Yudong Chen, and Martin J. Wainwright.
Preprint, 2015. [arXiv]



Mixture of linear regressions


Global Convergence of the EM Algorithm for Mixtures of Two Component Linear Regression
Jeongyeol Kwon, Wei Qian, Constantine Caramanis, Yudong Chen, and Damek Davis.
Conference on Learning Theory (COLT), 2019. [arxiv]

Learning Mixtures of Sparse Linear Regressions Using Sparse Graph Codes
Dong Yin, Ramtin Pedarsani, Yudong Chen, and Kannan Ramchandran.
IEEE Transactions on Information Theory, vol. 65, no. 3, pp. 1430-1451, 2019. [arxiv] [ieee link]
Partial preliminary results appeared in the 55th Annual Allerton Conference on Communication, Control, and Computing, 2017.

Convex and Nonconvex Formulations for Mixed Regression with Two Components: Minimax Optimal Rates
Yudong Chen, Xinyang Yi, and Constantine Caramanis.
IEEE Transactions on Information Theory, vol. 64, no. 3, pp. 1738-1766, 2018. [ieee link]
Partial preliminary results appeared under the title "A Convex Formulation for Mixed Regression with Two Components: Minimax Optimal Rates" at the Conference on Learning Theory (COLT), 2014. [pdf] [arxiv] 



Graph clustering and community detection


Achieving the Bayes Error Rate in Synchronization and Block Models by SDP, Robustly
Yingjie Fei and Yudong Chen.
IEEE Transactions on Information Theory, vol. 66, no. 6, pp. 3929-3953, 2020. [arxiv] [ieee link]
Partial preliminary results appeared in Conference on Learning Theory (COLT), 2019. [colt pdf]

Convex Relaxation Methods for Community Detection
Xiaodong Li, Yudong Chen, and Jiaming Xu.
Statistical Science, vol. 36, no. 1, pp. 2-15, 2021. [arxiv]

Hidden Integrality of SDP Relaxation for Sub-Gaussian Mixture Models
Yingjie Fei and Yudong Chen.
Conference on Learning Theory (COLT), 2018. [arxiv]
2nd Place, 2018 INFORMS George Nicholson Student Paper Competition.

Exponential error rates of SDP for block models: Beyond Grothendieck's inequality
Yingjie Fei and Yudong Chen.
IEEE Transactions on Information Theory, vol. 65, no. 1, pp. 551-571, 2019. [arxiv] [ieee link]

Clustering from General Pairwise Observations with Applications to Time-varying Graphs
Shiau Hong Lim, Yudong Chen, and Huan Xu.
Journal of Machine Learning Research (JMLR), 18(49), 1-47, 2017. [pdf] [jmlr link]
Partial preliminary resutls appeared in ICML and NIPS.

Convexified Modularity Maximization for Degree-corrected Stochastic Block Models
Yudong Chen, Xiaodong Li, and Jiaming Xu.
Annals of Statistics, vol. 46, no. 4, pp. 1573-1602, 2018. [arxiv] [web page and code]

A Convex Optimization Framework for Bi-Clustering
Shiau Hong Lim, Yudong Chen, and Huan Xu.
International Conference on Machine Learning (ICML), 2015. [pdf] [supplementary] [icml link]

Clustering from Labels and Time-Varying Graphs
Shiau Hong Lim, Yudong Chen, and Huan Xu.
Neural Information Processing Systems Conference (NIPS), 2014 (Spotlight). [pdf] [supplementary] [nips link]

Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices
Yudong Chen and Jiaming Xu.
Journal of Machine Learning Research (JMLR), vol. 17, no. 27, pp. 1-57, 2016. [pdf] [arXiv]
Partial results appeared at the International Conference on Machine Learning (ICML), 2014.

Weighted Graph Clustering with Non-uniform Uncertainties
Yudong Chen, Shiau Hong Lim, and Huan Xu.
International Conference on Machine Learning (ICML), 2014.  [pdf] [supplementary] [icml link]

Iterative and Active Graph Clustering Using Trace Norm Minimization Without Cluster Size Constraints
Nir Ailon, Yudong Chen, and Huan Xu.
Journal of Machine Learning Research (JMLR), vol. 16, pp. 450-490, March 2015. [pdf] [jmlr link] [arXiv]
Partial results appeared under the title "Breaking the Small Cluster Barrier of Graph Clustering" at the International Conference on Machine Learning (ICML), 2013.

Improved Graph Clustering
Yudong Chen, Sujay Sanghavi, and Huan Xu.
IEEE Transactions on Information Theory, vol. 60, no. 10, pp. 6440–6455, 2014. [ieee link] [arXiv]
Preliminary results appeared under the title "Clustering Sparse Graphs" in Advances in Neural Information Processing Systems 25 (NIPS), 2012. 

Detecting Overlapping Temporal Community Structure in Time-Evolving Networks
Yudong Chen, Vikas Kawadia, and Rahul Urgaonkar.
Technical Report, 2013. [arXiv]

Clustering Partially Observed Graphs via Convex Optimization
Yudong Chen, Ali Jalali, Sujay Sanghavi, and Huan Xu.
Journal of Machine Learning Research (JMLR), vol. 15, pp. 2213-2238, 2014. [pdf] [arXiv]
Partial preliminary results appeared at the International Conference on Machine Learning (ICML), 2011.



Low-rank matrix/tensor estimation


Tensor Robust Principal Component Analysis with A New Tensor Nuclear Norm
Canyi Lu, Jiashi Feng, Yudong Chen, Wei Liu, Zhouchen Lin, and Shuicheng Yan.
IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), vol. 42, no. 4, pp. 925-938, 2020. [arxiv] [ieee link]

Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
Canyi Lu, Jiashi Feng, Yudong Chen, Wei Liu, Zhouchen Lin, and Shuicheng Yan.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [pdf] 

Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees
Yudong Chen, Martin J. Wainwright.
Preprint, 2015. [arXiv]

Completing Any Low-Rank Matrix, Provably
Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, and Rachel Ward.
Journal of Machine Learnng Research (JMLR), vol. 16, pp. 2999-3034, 2015. [pdf] [jmlr link]
Partial results appeared at the International Conference on Machine Learning (ICML) 2014.

Incoherence-Optimal Matrix Completion
Yudong Chen.
IEEE Transactions on Information Theory, vol. 61, no. 5, pp. 2909-2923, 2015. [ieee link] [arXiv]

Matrix Completion with Column Manipulation: Near-Optimal Sample-Robustness-Rank Tradeoffs
Yudong Chen, Huan Xu, Constantine Caramanis, and Sujay Sanghavi.
IEEE Transactions on Information Theory, vol. 62, no. 1, pp. 503-526, 2016. [arxiv] [ieee link]
Partial preliminary results appeared at the International Conference on Machine Learning (ICML), 2011.

Low-rank Matrix Recovery from Errors and Erasures
Yudong Chen, Ali Jalali, Sujay Sanghavi, and Constantine Caramanis.
IEEE Transactions on Information Theory, vol. 59, no. 7, pp. 4324-4337, 2013. [ieee link] [arXiv]
Partial preliminary results appeared at the International Symposium on Information Theory (ISIT), 2011.



Sparse and robust regression

Robust Sparse Regression under Adversarial Corruption
Yudong Chen, Constantine Caramanis, and Shie Mannor.
The International Conference on Machine Learning (ICML), 2013. [pdf] [supplementary]
An earlier version of the paper with weaker results is available on [arXiv]

Noisy and Missing Data Regression: Distribution-Oblivious Support Recovery
Yudong Chen and Constantine Caramanis.
The International Conference on Machine Learning (ICML), 2013. [pdf] [supplementary]
An earlier version of the paper with partial results is available on [arXiv].

Simple Algorithms for Sparse Linear Regression with Noisy and Missing Data
Yudong Chen and Constantine Caramanis.
2012 IEEE Statistical Signal Processing Workshop (SSP'12).



Wireless networks, signal processing and kernel methods

Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
Fanghui Liu, Xiaolin Huang, Yudong Chen, and Johan A.K. Suykens
Preprint, 2020. [arxiv]

Random Fourier Features via Fast Surrogate Leverage Weighted Sampling
Fanghui Liu, Xiaolin Huang, Yudong Chen, Jie Yang, and Johan Suykens
Association for the Advancement of Artificial Intelligence Conference (AAAI), 2020. [arxiv]

User Association for Load Balancing in Heterogeneous Cellular Networks
Qiaoyang Ye, Beiyu Rong, Yudong Chen, Mazin Al-Shalash, Constantine Caramanis, and Jeffrey G. Andrews.
IEEE Transactions on Wireless Communications, vol. 12, no. 6, pp. 2706-2716, 2013. [ieee link] [arXiv]
Partial preliminary results appeared at IEEE Globecom 2012.

Quantization Errors of Uniformly Quantized fGn and fBm Signals
Zhiheng Li, Yudong Chen, Li Li, and Yi Zhang.
IEEE Signal Processing Letters, vol. 16, no. 12, 1059-1062, 2009. [arXiv]

PCA Based Hurst Exponent Estimator for fBm Signals under Disturbances
Li Li, Jianming Hu, Yudong Chen, and Yi Zhang.
IEEE Transactions on Signal Processing, vol. 57, no. 7, 2840-2846, 2009.



Intelligent transportation systems


Mining for Similarities in Urban Traffic Flow Using Wavelets
Yudong Chen, Yi Zhang, Jianming Hu, and Li Li.
Proceedings of IEEE International Conference on Intelligent Transportation System (ITSC‘07), 2007.

Pattern Discovering of Regional Traffic Status with Self-Organizing Maps
Yudong Chen, Yi Zhang and Jianming Hu.
Proceedings of IEEE International Conference on Intelligent Transportation System (ITSC’06), 2006.


[Home]  [Publications (chronological order)]  [Publications (by type)]