Yudong Chen    


Department of Electrical Engineering and Computer Sciences
University of California, Berkeley
264 Cory Hall, MC 1768, Berkeley, CA 94720
yudong.chen at eecs dot berkeley dot edu
(or: ydchen at utexas dot edu)

[Bio]  [Publications (by year) (by topic) (by type)]  [Courses]  [Teaching]

Bio

I am a postdoc in the EECS department at the University of California, Berkeley working with Martin J. Wainwright. My research interests include machine learning, robust statistics, convex optimization, and their applications in graph clustering and community detection.

I obtained my Ph.D. in Electrical and Computer Engineering from The University of Texas at Austin in 2013. My advisor was Constantine Caramanis, and I was also fortunate to work with Sujay Sanghavi, Huan Xu, and Shie Mannor.  I received my B.S. and M.S. from Tsinghua University. I spent a wonderful summer in 2005 at National Tsing Hua University as an exchange student, and have worked at Raytheon BBN, IBM and Siemens as an intern.  I was an academic visitor at the National University of Singapore in 2014.

I am currently on the job market.

Publications (By Year)

  [By Topic]  [By Type]

2014

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

A Convex Formulation for Mixed Regression with two Components: Minimax Optimal Rates,
Yudong Chen, Xinyang Yi, and Constantine Caramanis.
The Conference on Learning Theory (COLT) 2014. [pdf]
An earlier version of the paper with partial results is available on [arXiv]

Statistical-Computational Tradeoffs in Planted Problems and Submatrix Localization with a Growing Number of Clusters and Submatrices,
Yudong Chen and Jiaming Xu. [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.
The International Conference on Machine Learning (ICML) 2014. [link]

Coherent Matrix Completion,
Yudong Chen, Srinadh Bhojanapalli, Sujay Sanghavi, and Rachel Ward.
Journal of Machine Learnng Research (JMLR), under revision, 2014. [arXiv]
Partial results appeared at the International Conference on Machine Learning (ICML) 2014.

2013

Incoherence-Optimal Matrix Completion,
Yudong Chen.
Submitted, 2013. [arXiv]

Breaking the Small Cluster Barrier of Graph Clustering,
Nir Ailon, Yudong Chen, and Huan Xu.
Journal of Machine Learning Research (JMLR), to appear, 2014. [arXiv]
Partial results appeared at the International Conference on Machine Learning (ICML) 2013.

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]. Also presented in 2012 IEEE Statistical Signal Processing Workshop SSP'12.

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

2012

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

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. [link] [arXiv]
Partial preliminary results appeared at IEEE Globecom 2012.

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. [link] [arXiv]
Partial preliminary results appeared at the International Symposium on Information Theory (ISIT), 2011.

2011 and Earlier

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. [link] [arXiv]
Partial preliminary results appeared at the International Conference on Machine Learning (ICML), 2011.

Robust Matrix Completion with Corrupted Columns,
Yudong Chen, Huan Xu, Constantine Caramanis, and Sujay Sanghavi.
Submitted. [arXiv]
Partial preliminary results appeared at the International Conference on Machine Learning (ICML), 2011.

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,
with Li Li, Jianming Hu, Yudong Chen, and Yi Zhang.
IEEE Transactions on Signal Processing, vol. 57, no. 7, 2840-2846, 2009.

Courses

Learning Theory, Randomized Algorithms, Information Theory, Convex Optimization Theory, Linear Programming, Stochastic Control Theory, Probability and Stochastic Processes, Theory of Probability (Measure Theory), Topics in Network Sciences, Sparsity/Structure/Algorithms, Data Mining, Analysis and Design of Communication Networks.

Teaching

In Fall 2011, I was a teaching assistant and leturer of EE381V, UT-Austin's graduate course on Convex Analysis and Optimization.