Conference proceeding
Recovering the Optimal Solution by Dual Random Projection
Proceedings of Machine Learning Research, Vol.30, pp.135-157
2013
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.
Details
- Title: Subtitle
- Recovering the Optimal Solution by Dual Random Projection
- Creators
- Lijun ZhangMehrdad MahdaviRong JinTianbao YangShenghuo Zhu
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of Machine Learning Research, Vol.30, pp.135-157
- Language
- English
- Date published
- 2013
- Academic Unit
- Computer Science
- Record Identifier
- 9984259491302771
Metrics
10 Record Views