GADMM solves convex distributed learning over a chain topology with alternating head/tail updates and two-neighbor communication, and provably converges.
Distributed large-scale natural graph factorization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
GADMM: Fast and Communication Efficient Framework for Distributed Machine Learning
GADMM solves convex distributed learning over a chain topology with alternating head/tail updates and two-neighbor communication, and provably converges.