# Distributed Nesterov gradient methods over arbitrary graphs

21 Jan 2019Ran XinDusan JakoveticUsman A. Khan

In this letter, we introduce a distributed Nesterov method, termed as $\mathcal{ABN}$, that does not require doubly-stochastic weight matrices. Instead, the implementation is based on a simultaneous application of both row- and column-stochastic weights that makes this method applicable to arbitrary (strongly-connected) graphs... (read more)

PDF Abstract

No code implementations yet. Submit your code now