자료유형 | 학위논문 |
---|---|
서명/저자사항 | Algorithms for Statistical and Interactive Learning Tasks. |
개인저자 | Tosh, Christopher. |
단체저자명 | University of California, San Diego. Computer Science. |
발행사항 | [S.l.]: University of California, San Diego., 2018. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2018. |
형태사항 | 252 p. |
기본자료 저록 | Dissertation Abstracts International 79-12B(E). Dissertation Abstract International |
ISBN | 9780438169203 |
학위논문주기 | Thesis (Ph.D.)--University of California, San Diego, 2018. |
일반주기 |
Source: Dissertation Abstracts International, Volume: 79-12(E), Section: B.
Adviser: Sanjoy Dasgupta. |
요약 | In the first part of this thesis, we examine the computational complexity of three fundamental statistical tasks: maximum likelihood estimation, maximum a posteriori estimation, and approximate posterior sampling. We show that maximum likelihood |
요약 | In the second part of this thesis, we explore the behavior of a common sampling algorithm known as the Gibbs sampler. We show that in the context of Bayesian Gaussian mixture models, this algorithm can take a very long time to converge, even whe |
요약 | In the third part of this thesis, we consider learning problems in which the learner is allowed to solicit interaction from a user. In the context of classification, we present an efficient active learning algorithm whose performance is guarante |
일반주제명 | Computer science. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |