Active Learning and Submodular Functions

ResearchWorks/Manakin Repository

Search ResearchWorks


Advanced Search

Browse

My Account

Statistics

Related Information

Active Learning and Submodular Functions

Show simple item record

dc.contributor.advisor Bilmes, Jeffrey A en_US
dc.contributor.author Guillory, Andrew Russell en_US
dc.date.accessioned 2012-09-13T17:33:00Z
dc.date.available 2012-09-13T17:33:00Z
dc.date.issued 2012-09-13
dc.date.submitted 2012 en_US
dc.identifier.other Guillory_washington_0250E_10517.pdf en_US
dc.identifier.uri http://hdl.handle.net/1773/20751
dc.description Thesis (Ph.D.)--University of Washington, 2012 en_US
dc.description.abstract Active learning is a machine learning setting where the learning algorithm decides what data is labeled. Submodular functions are a class of set functions for which many optimization problems have efficient exact or approximate algorithms. We examine their connections. 1. We propose a new class of interactive submodular optimization problems which connect and generalize submodular optimization and active learning over a finite query set. We derive greedy algorithms with approximately optimal worst-case cost. These analyses apply to exact learning, approximate learning, learning in the presence of adversarial noise, and applications that mix learning and covering. 2. We consider active learning in a batch, transductive setting where the learning algorithm selects a set of examples to be labeled at once. In this setting we derive new error bounds which use symmetric submodular functions for regularization, and we give algorithms which approximately minimize these bounds. 3. We consider a repeated active learning setting where the learning algorithm solves a sequence of related learning problems. We propose an approach to this problem based on a new online prediction version of submodular set cover. A common theme in these results is the use of tools from submodular optimization to extend the breadth and depth of learning theory with an emphasis on non-stochastic settings. en_US
dc.format.mimetype application/pdf en_US
dc.language.iso en_US en_US
dc.subject active learning; machine learning; submodular functions en_US
dc.subject.other Computer science en_US
dc.subject.other Artificial intelligence en_US
dc.subject.other Computer science and engineering en_US
dc.title Active Learning and Submodular Functions en_US
dc.type Thesis en_US
dc.embargo.terms No embargo en_US


Files in this item

Files Size Format View
Guillory_washington_0250E_10517.pdf 1.422Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record