Truncated Power Method for Sparse Eigenvalue Problems
Xiao-Tong Yuan
Postdoctoral Research Associate
Department of Statistical Science, Cornell University
Abstract: The sparse eigenvalue problem is to extract dominant (largest) sparse eigenvectors with at most k non-zero components. In this talk, I’m going to introduce a simple yet effective solution called truncated power method that can approximately solve this underlying non-convex optimization problem. A strong sparse recovery result is proved for the truncated power method, and this theory is our key motivation for developing the new algorithm. The proposed method is tested on applications such as sparse principal component analysis and densest k-subgraph finding problem. Extensive experiments on several synthetic and real-world large scale datasets demonstrate the competitive empirical performance of our method.
Bio：Dr. Xiao-Tong Yuan is presently working as a postdoctoral research associate at Department of Statistical Science, Cornell University. Prior to that, he worked as a postdoctoral research fellow at Department of Statistics, Rutgers University. He received Ph.D. degree in Pattern Recognition and Intelligent System at National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences. His main research interests are in statistical machine learning, data mining, and computer vision. He has authored or co-authored over 40 technical papers over a wide range of research topics. He received the winner prizes of the classification task in PASCAL VOC 2010.