INDIGO Home University of Illinois at Urbana-Champaign logo uic building uic pavilion uic student center

Problems in Learning under Limited Resources and Information

Show full item record

Bookmark or cite this item: http://hdl.handle.net/10027/21988

Files in this item

File Description Format
PDF HUANG-DISSERTATION-2017.pdf (2MB) (no description provided) PDF
Title: Problems in Learning under Limited Resources and Information
Author(s): Huang, Yi
Advisor(s): Reyzin, Lev
Contributor(s): DasGupta, Bhaskar; Mubayi, Dhruv; Turan, Gyorgy; Sloan, Robert; Ziebart, Brian; Reyzin, Lev
Department / Program: Mathematics, Statistics, and Computer Science
Degree Granting Institution: University of Illinois at Chicago
Degree: PhD, Doctor of Philosophy
Genre: Doctoral
Subject(s): feature-efficient learning network construction
Abstract: The main theme of this thesis is to investigate how learning problems can be solved in the face of limited resources and with limited information to base inferences on. We study feature-efficient prediction when each feature comes with a cost and our goal is to construct a good predictor during training time with total cost not exceeding the given budget constraints. We also study complexity-theoretic properties of models for recovering social networks with knowledge only about how people in the network vote or how information propagates through the network.
Issue Date: 2017-08-16
Type: Thesis
URI: http://hdl.handle.net/10027/21988
Date Available in INDIGO: 2017-11-01
Date Deposited: August 201
 

This item appears in the following Collection(s)

Show full item record

Statistics

Country Code Views
Ukraine 21
United States of America 14
China 10
Germany 3
United Kingdom 1

Browse

My Account

Information

Access Key