Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/134432
Title: OPTIMIZATION AND LEARNING UNDER UNCERTAINTY - A UNIFIED ROBUSTNESS PERSPECTIVE
Authors: YANG WENZHUO
Keywords: machine learning, robust optimization, chance constraint, pca, dimension reduction, classification
Issue Date: 8-Aug-2016
Source: YANG WENZHUO (2016-08-08). OPTIMIZATION AND LEARNING UNDER UNCERTAINTY - A UNIFIED ROBUSTNESS PERSPECTIVE. ScholarBank@NUS Repository.
Abstract: Robust decision making is ubiquitous in real-world applications in machine learning, operations research and finance, etc., due to the existence of uncertainty and noise coming from measurement errors or malicious attacking. This thesis first investigates the computational aspects of distributionally robust chance constrained optimization with non-linear uncertainties, and apply this technique in machine learning both theoretically and algorithmically, i.e., we provide a new robustness interpretation of Lasso-like algorithms and regularized SVMs. Second, we consider optimization problems with unknown parameters and tackle them from a dynamic perspective: the decision maker can make a tentative decision, collect the corresponding feedbacks, and fine tune the decision. To numerically solve them, we develop and analyze two algorithms based on the epsilon-decreasing strategy and the upper confidence bound strategy, respectively. Finally, we study the dimension reduction problem with noisy and outlying observation, and propose three outlier-robust principal component analysis algorithms with solid theoretical performance guarantees.
URI: http://scholarbank.nus.edu.sg/handle/10635/134432
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
thesis_final.pdf5.38 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

119
checked on Jan 21, 2018

Download(s)

86
checked on Jan 21, 2018

Google ScholarTM

Check


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