Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1

30 May 2019Majid JahaniMohammadreza NazariSergey RusakovAlbert S. BerahasMartin Takáč

In this paper, we present a scalable distributed implementation of the Sampled Limited-memory Symmetric Rank-1 (S-LSR1) algorithm. First, we show that a naive distributed implementation of S-LSR1 requires multiple rounds of expensive communications at every iteration and thus is inefficient... (read more)

PDF Abstract


No code implementations yet. Submit your code now


Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.