dc.contributor.advisor | Gray, Alexander | |
dc.contributor.author | Ganti Mahapatruni, Ravi Sastry | |
dc.date.accessioned | 2014-05-22T15:23:35Z | |
dc.date.available | 2014-05-22T15:23:35Z | |
dc.date.created | 2014-05 | |
dc.date.issued | 2014-01-10 | |
dc.date.submitted | May 2014 | |
dc.identifier.uri | http://hdl.handle.net/1853/51801 | |
dc.description.abstract | In this thesis, we provide computationally efficient algorithms with provable statistical guarantees, for the problem of active learning, by using ideas from sequential analysis. We provide a generic algorithmic framework for active learning in the pool setting, and instantiate this framework by using ideas from learning with experts, stochastic optimization, and multi-armed bandits. For the problem of learning convex combination of a given set of hypothesis, we provide a stochastic mirror descent based active learning algorithm in the stream setting. | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.publisher | Georgia Institute of Technology | |
dc.subject | Active learning | |
dc.subject | Sequential analysis | |
dc.subject | Stochastic optimization | |
dc.subject.lcsh | Active learning | |
dc.subject.lcsh | Algorithms | |
dc.subject.lcsh | Sequential analysis | |
dc.subject.lcsh | Mathematical optimization | |
dc.subject.lcsh | Machine learning | |
dc.title | New formulations for active learning | |
dc.type | Dissertation | |
dc.description.degree | Ph.D. | |
dc.contributor.department | Computer Science | |
thesis.degree.level | Doctoral | |
dc.contributor.committeeMember | Balcan, Maria-Florina | |
dc.contributor.committeeMember | Song, Le | |
dc.contributor.committeeMember | Rakhlin, Alexander | |
dc.contributor.committeeMember | Zhang, Tong | |
dc.date.updated | 2014-05-22T15:23:35Z | |