FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W8662893> ?p ?o ?g. }

• W8662893 abstract "Author(s): Towfic, Zaid Joseph | Advisor(s): Sayed, Ali H | Abstract: Distributed convex optimization refers to the task of minimizing the aggregate sum of convex risk functions, each available at an agent of a connected network, subject to convex constraints that are also distributed across the agents. The risk functions at the agents are generally defined as expectations of certain loss functions, with the expectations computed over the statistical distribution of the data. One of the key challenges in solving such optimization problems is that the agents are only subjected to streaming data realizations and they are not aware of the underlying statistical models. Accordingly, each agent is only aware of its loss function and does not have sufficient information to evaluate its risk function. Another key challenge is that each agent is only aware of its constraints. This dissertation develops and studies fully decentralized first-order strategies to solve such problems. The first class of strategies considered in this work belongs to the family of primal-dual methods, which rely on propagating two sets of variables: the primal variable and a dual variable. In contrast to the traditional treatment of these algorithms in the optimization literature, this dissertation develops primal-dual methods for adaptation and learning from streaming data over networks. In this case, the optimization problem is not necessarily static since its minimizer can drift with time and the exact form of the cost function is not known beforehand. Fully-distributed and adaptive variants of the Arrow-Hurwicz (AH) and augmented Lagrangian (AL) methods are developed by resorting to stochastic-gradient approximations. The stability range and the performance limits of the resulting strategies are analyzed. Several revealing results are discovered including the fact that primal-dual techniques tend to have a smaller stability range and a degraded performance in comparison to primal techniques, such as consensus and diffusion strategies. This conclusion suggests that AH and AL techniques are not as reliable for adaptation over networks and the advantages of AH and AL techniques in the static optimization context do not necessarily carry over to the stochastic context.The dissertation subsequently focuses on developing primal optimization methods of the diffusion type for the distributed solution of a general class of constrained optimization problems. Most available distributed solutions for these types of problems rely on the use of projection steps in order to ensure that the successive iterates at the nodes satisfy the convex constraints. In these solutions, the constraint conditions need to be relatively simple in order for the distributed algorithm to be able to compute the necessary projections analytically (such as projecting onto the nonnegative orthant). This work proposes a new class of distributed solutions that employ constant step-sizes and that eliminate the need for projection steps. The solution technique relies instead on the use of suitably chosen penalty functions and replaces the projection step by a stochastic approximation update that run concurrently with the optimization step. The challenge is to show that the use of penalty functions in the stochastic gradient update step still leads to accurate solutions. The analysis in the dissertation establishes that this is indeed possible. Moreover, in the proposed solution, the nodes are only required to interact locally and to have access to local iterates from their neighbors; there is no need for the nodes to know any of the constraints besides their own." @default.
• W8662893 created "2016-06-24" @default.
• W8662893 creator A5054060991 @default.
• W8662893 date "2014-01-01" @default.
• W8662893 modified "2023-09-27" @default.
• W8662893 title "Online Learning Over Networks" @default.
• W8662893 hasPublicationYear "2014" @default.
• W8662893 type Work @default.
• W8662893 sameAs 8662893 @default.
• W8662893 citedByCount "0" @default.
• W8662893 crossrefType "journal-article" @default.
• W8662893 hasAuthorship W8662893A5054060991 @default.
• W8662893 hasConcept C112680207 @default.
• W8662893 hasConcept C126255220 @default.
• W8662893 hasConcept C137836250 @default.
• W8662893 hasConcept C14036430 @default.
• W8662893 hasConcept C145446738 @default.
• W8662893 hasConcept C157972887 @default.
• W8662893 hasConcept C2524010 @default.
• W8662893 hasConcept C26517878 @default.
• W8662893 hasConcept C33923547 @default.
• W8662893 hasConcept C38652104 @default.
• W8662893 hasConcept C41008148 @default.
• W8662893 hasConcept C78458016 @default.
• W8662893 hasConcept C86803240 @default.
• W8662893 hasConceptScore W8662893C112680207 @default.
• W8662893 hasConceptScore W8662893C126255220 @default.
• W8662893 hasConceptScore W8662893C137836250 @default.
• W8662893 hasConceptScore W8662893C14036430 @default.
• W8662893 hasConceptScore W8662893C145446738 @default.
• W8662893 hasConceptScore W8662893C157972887 @default.
• W8662893 hasConceptScore W8662893C2524010 @default.
• W8662893 hasConceptScore W8662893C26517878 @default.
• W8662893 hasConceptScore W8662893C33923547 @default.
• W8662893 hasConceptScore W8662893C38652104 @default.
• W8662893 hasConceptScore W8662893C41008148 @default.
• W8662893 hasConceptScore W8662893C78458016 @default.
• W8662893 hasConceptScore W8662893C86803240 @default.
• W8662893 hasLocation W86628931 @default.
• W8662893 hasOpenAccess W8662893 @default.
• W8662893 hasPrimaryLocation W86628931 @default.
• W8662893 hasRelatedWork W1777097917 @default.
• W8662893 hasRelatedWork W1976179273 @default.
• W8662893 hasRelatedWork W2045154709 @default.
• W8662893 hasRelatedWork W2049396938 @default.
• W8662893 hasRelatedWork W2086502731 @default.
• W8662893 hasRelatedWork W2114791779 @default.
• W8662893 hasRelatedWork W2136517470 @default.
• W8662893 hasRelatedWork W2162594647 @default.
• W8662893 hasRelatedWork W2174036086 @default.
• W8662893 hasRelatedWork W2188344180 @default.
• W8662893 hasRelatedWork W2299935480 @default.
• W8662893 hasRelatedWork W2610994321 @default.
• W8662893 hasRelatedWork W2889634868 @default.
• W8662893 hasRelatedWork W2912682655 @default.
• W8662893 hasRelatedWork W2921611804 @default.
• W8662893 hasRelatedWork W2963730255 @default.
• W8662893 hasRelatedWork W2966854558 @default.
• W8662893 hasRelatedWork W3035078398 @default.
• W8662893 hasRelatedWork W3154856134 @default.
• W8662893 hasRelatedWork W3166255866 @default.
• W8662893 isParatext "false" @default.
• W8662893 isRetracted "false" @default.
• W8662893 magId "8662893" @default.
• W8662893 workType "article" @default.