자료유형 | 학위논문 |
---|---|
서명/저자사항 | Exact Diffusion Learning Over Networks. |
개인저자 | Yuan, Kun. |
단체저자명 | University of California, Los Angeles. Electrical and Computer Engineering 0333. |
발행사항 | [S.l.]: University of California, Los Angeles., 2019. |
발행사항 | Ann Arbor: ProQuest Dissertations & Theses, 2019. |
형태사항 | 265 p. |
기본자료 저록 | Dissertations Abstracts International 81-06B. Dissertation Abstract International |
ISBN | 9781687966254 |
학위논문주기 | Thesis (Ph.D.)--University of California, Los Angeles, 2019. |
일반주기 |
Source: Dissertations Abstracts International, Volume: 81-06, Section: B.
Advisor: Sayed, Ali H. |
이용제한사항 | This item must not be sold to any third party vendors. |
요약 | In this dissertation, we study optimization, adaptation, and learning problems over connected networks. In these problems, each agent $k$ collects and learns from its own local data and is able to communicate with its local neighbors. While each single node in the network may not be capable of sophisticated behavior on its own, the agents collaborate to solve large-scale and challenging learning problems.Different approaches have been proposed in the literature to boost the learning capabilities of networked agents. Among these approaches, the class of diffusion strategies has been shown to be particularly well-suited due to their enhanced stability range over other methods and improved performance in adaptive scenarios. However, diffusion implementations suffer from a small inherent bias in the iterates. When a constant step-size is employed to solve deterministic optimization problems, the iterates generated by the diffusion strategy will converge to a small neighborhood around the desired global solution but not to the exact solution itself. This bias is not due to any gradient noise arising from stochastic approximation |
일반주제명 | Electrical engineering. |
언어 | 영어 |
바로가기 |
: 이 자료의 원문은 한국교육학술정보원에서 제공합니다. |