Recovering the Optimal Solution by Dual Random Projection¶
Rong Jin
Associate Professor
Department of Computer Science and Engineering, Michigan State University
Abstract: Random projection has been widely used in data classification. It maps high-dimensional data into a low-dimensional subspace in order to reduce the computational cost in solving the related optimization problem. While previous studies are focused on analyzing the classification performance of using random projection, in this work, we consider the recovery problem, i.e., how to accurately recover the optimal solution to the original optimization problem in the high-dimensional space based on the solution learned from the subspace spanned by random projections. We present a simple algorithm, termed Dual Random Projection, that uses the dual solution of the low-dimensional optimization problem to recover the optimal solution to the original problem. Our theoretical analysis shows that with a high probability, the proposed algorithm is able to accurately recover the optimal solution to the original problem, provided that the data matrix is of low rank or can be well approximated by a low rank matrix.
Bio: Rong Jin focuses his research on statistical machine learning and its application to information retrieval. He has worked on a variety of machine learning algorithms and their application to information retrieval, including retrieval models, collaborative filtering, cross lingual information retrieval, document clustering, and video/image retrieval. He has published over 160 conference and journal articles on related topics. Dr. Jin Ph.D. holds a Ph.D. in Computer Science from Carnegie Mellon University He received the NSF Career Award in 2006.