DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Yang, Hongseok | - |
dc.contributor.advisor | 양홍석 | - |
dc.contributor.author | Yu, Hangyeol | - |
dc.date.accessioned | 2021-05-13T19:38:20Z | - |
dc.date.available | 2021-05-13T19:38:20Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=925160&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284999 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2020.8,[iii, 38 p. :] | - |
dc.description.abstract | Probabilistic programming languages offer powerful generic inference algorithms to let programmers write probabilistic models with succinct programming notations. Stochastic variational inference (SVI) is one of the most popular classes of such inference algorithms. However, many verification challenges arise to assure that a given probabilistic program runs a valid SVI. Among those, this dissertation aims at the verification of well-defined variational objectives. We define a Pyro-like probabilistic programming language and its denotational semantics using a special data structure called random database. Then, we propose a sufficient set of conditions for the bounded evidence lower bound (ELBO), which is the most fundamental variational objective. The most remarkable condition is the finite expected execution time of a program, whose verification is a well-studied research problem. Finally, we generalized our result to three other variational objectives. The next challenge is to develop an automatic program analyzer based on our current knowledge. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | probabilistic programming language▼astochastic variational inference▼awell-definedness▼adenotational semantics▼arandom database▼aaverage running time | - |
dc.subject | 확률적 프로그래밍 언어▼a변분 추론▼a잘 정의됨▼a표시적 의미론▼a랜덤 데이터베이스▼a평균 실행 시간 | - |
dc.title | Verifying well-definedness of variational objectives for probabilistic programs | - |
dc.title.alternative | 확률적 프로그램의 잘 정의된 변분 목적 함수 검증 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 유한결 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.