Show simple item record

dc.contributor.advisorBilmes, Jeffrey Aen_US
dc.contributor.authorGuillory, Andrew Russellen_US
dc.date.accessioned2012-09-13T17:33:00Z
dc.date.available2012-09-13T17:33:00Z
dc.date.issued2012-09-13
dc.date.submitted2012en_US
dc.identifier.otherGuillory_washington_0250E_10517.pdfen_US
dc.identifier.urihttp://hdl.handle.net/1773/20751
dc.descriptionThesis (Ph.D.)--University of Washington, 2012en_US
dc.description.abstractActive 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.mimetypeapplication/pdfen_US
dc.language.isoen_USen_US
dc.rightsCopyright is held by the individual authors.en_US
dc.subjectactive learning; machine learning; submodular functionsen_US
dc.subject.otherComputer scienceen_US
dc.subject.otherArtificial intelligenceen_US
dc.subject.otherComputer science and engineeringen_US
dc.titleActive Learning and Submodular Functionsen_US
dc.typeThesisen_US
dc.embargo.termsNo embargoen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record