(A) fast and memory-efficient software framework for differentially private machine learning차등 정보보호 머신 러닝을 위한 메모리-효율적인 고속 소프트웨어 프레임워크 설계

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 88
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorRhu, Minsoo-
dc.contributor.advisor유민수-
dc.contributor.authorPark, Beomsik-
dc.date.accessioned2023-06-26T19:34:20Z-
dc.date.available2023-06-26T19:34:20Z-
dc.date.issued2023-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032937&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/309961-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2023.2,[iii, 24 p. :]-
dc.description.abstractThis paper proposed a new high-performant differentially private machine learning framework. It reduces the overall memory usage and increases training throughput while providing a mathematically same result. The proposed framework consisted of two major components, which are example-wise weight gradients computation and adaptive clipping. By implementing an end-to-end DP-SGD framework which utilizes these components, it is shown that a new framework can reduces the memory usage and increases training throughput.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subject컴퓨터 아키텍처▼a머신 러닝▼a차등 정보보호-
dc.subjectDifferential privacy▼aMachine learning▼aComputer architecture-
dc.title(A) fast and memory-efficient software framework for differentially private machine learning-
dc.title.alternative차등 정보보호 머신 러닝을 위한 메모리-효율적인 고속 소프트웨어 프레임워크 설계-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학부,-
dc.contributor.alternativeauthor박범식-
Appears in Collection
EE-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0