Recovering the optimal solution by dual random projection

Lijun Zhang, Mehrdad Mahdavi, Rong Jin, Tianbao Yang, Shenghuo Zhu

Research output: Contribution to journalConference article

24 Scopus citations

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.

Original languageEnglish (US)
Pages (from-to)135-157
Number of pages23
JournalJournal of Machine Learning Research
Volume30
StatePublished - Jan 1 2013
Event26th Conference on Learning Theory, COLT 2013 - Princeton, NJ, United States
Duration: Jun 12 2013Jun 14 2013

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Recovering the optimal solution by dual random projection'. Together they form a unique fingerprint.

  • Cite this