Transcription of Distributed Optimization and Statistical Learning via the ...
{{id}} {{{paragraph}}}
Foundations and TrendsR inMachine LearningVol. 3, No. 1 (2010) 1 122c 2011 S. Boyd, N. Parikh, E. Chu, B. Peleatoand J. EcksteinDOI: Optimization and StatisticalLearning via the Alternating DirectionMethod of MultipliersStephen Boyd1, Neal Parikh2, Eric Chu3 Borja Peleato4and Jonathan Eckstein51 Electrical Engineering Department, Stanford University, Stanford, CA94305, USA, Science Department, Stanford University, Stanford, CA 94305,USA, Engineering Department, Stanford University, Stanford, CA94305, USA, Engineering Department, Stanford University, Stanford, CA94305, USA, Science and Information Systems Department andRUTCOR, Rutgers University, Piscataway, NJ 08854.
method of multipliers, two important precursors to ADMM. This sec-tion is intended mainly for background and can be skimmed. In §3, we present ADMM, including a basic convergence theorem, some vari-ations on the basic version that are useful in practice, and a survey of some of the key literature. A complete convergence proof is given in ...
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}