Selective algorithms for large-scale classification and structured learning

The desired output in many machine learning tasks is a structured object, such as tree, clustering, or sequence. Learning accurate prediction models for such problems requires training on large amounts of data, making use of expressive features and performing global inference that simultaneously assigns values to all interrelated nodes in the structure. All these contribute to significant scalability problems. In this thesis, we describe a collection of results that address several aspects of these problems – by carefully selecting and caching samples, structures, or latent items. Our results lead to efficient learning algorithms for large-scale binary classification models, structured prediction models and for online clustering models which, in turn, support reduction in problem size, improvements in training and evaluation speed and improved performance. We have used our algorithms to learn expressive models from large amounts of annotated data and achieve state-of-the art performance on several natural language processing tasks.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2015

Author dc:creator

• Chang, Kai-Wei

Contributors dc:contributor

• Roth, Dan
• Forsyth, David A.
• Zhai, ChengXiang
• Platt, John

• Selective Learning Algorithm
• Machine Learning
• Structured Learning
• Large-Scale Learning

Statement dc:rights

• Copyright 2015 Kai-Wei Chang

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/78437

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F78437