Sökning: onr:"swepub:oai:DiVA.org:kth-287512" >
Advances in Asynchr...
Advances in Asynchronous Parallel and Distributed Optimization
-
- Assran, By Mahmoud (författare)
- McGill Univ, Dept Elect & Comp Engn, Montreal, PQ H3A 0G4, Canada.
-
- Aytekin, Arda (författare)
- Ericsson AB, S-16440 Stockholm, Sweden.
-
- Feyzmahdavian, Hamid Reza (författare)
- ABB, S-72226 Stockholm, Sweden.
-
visa fler...
-
- Johansson, Mikael (författare)
- KTH,Reglerteknik
-
- Rabbat, Michael G. (författare)
- Facebook Inc, Dept AI Res, Montreal, PQ H2S 3G9, Canada.
-
visa färre...
-
McGill Univ, Dept Elect & Comp Engn, Montreal, PQ H3A 0G4, Canada Ericsson AB, S-16440 Stockholm, Sweden. (creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2020
- 2020
- Engelska.
-
Ingår i: Proceedings of the IEEE. - : Institute of Electrical and Electronics Engineers (IEEE). - 0018-9219 .- 1558-2256. ; 108:11, s. 2013-2031
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Motivated by large-scale optimization problems arising in the context of machine learning, there have been several advances in the study of asynchronous parallel and distributed optimization methods during the past decade. Asynchronous methods do not require all processors to maintain a consistent view of the optimization variables. Consequently, they generally can make more efficient use of computational resources than synchronous methods, and they are not sensitive to issues like stragglers (i.e., slow nodes) and unreliable communication links. Mathematical modeling of asynchronous methods involves proper accounting of information delays, which makes their analysis challenging. This article reviews recent developments in the design and analysis of asynchronous optimization methods, covering both centralized methods, where all processors update a master copy of the optimization variables, and decentralized methods, where each processor maintains a local copy of the variables. The analysis provides insights into how the degree of asynchrony impacts convergence rates, especially in stochastic optimization methods.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Nyckelord
- Program processors
- Optimization methods
- Machine learning
- Computational modeling
- Convergence
- Computational efficiency
- Distributed algorithms
- machine learning algorithms
- parallel algorithms
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas