Please use this identifier to cite or link to this item:
Title: Robust low-dimensional structure learning for big data and its applications
Keywords: robust, structure learning, low-dimensional, big data, machine learning, computer vision
Issue Date: 7-Feb-2014
Citation: FENG JIASHI (2014-02-07). Robust low-dimensional structure learning for big data and its applications. ScholarBank@NUS Repository.
Abstract: The explosive growth of data in the era of big data has presented great challenges to traditional structure learning techniques. In this thesis, we propose deterministic and online learning methods for robustly recovering the low-dimensional structure of big data. We first develop a DHRPCA method to recover low-dimensional subspace of high-dimensional data. DHRPCA possesses maximal robustness, and is asymptotically consistent in the high-dimensional space. Moreover, it exhibits significantly high efficiency for handling big data. Second, we propose two online learning methods, OR-PCA and online RPCA, to further enhance the scalability for robustly learning the low-dimensional structure of big data, under limited memory and computational cost budget. Third, we devise two low-dimensional learning algorithms for visual data analysis: (1) geometric feature pooling, and (2) auto-grouped sparse representation. These two methods achieve state-of-the-art performance on several benchmark image classification datasets.
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Jiashi_FENG_Phd_Thesis_Final.pdf2.22 MBAdobe PDF



Page view(s)

checked on May 11, 2020


checked on May 11, 2020

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.