Decentralized optimization with non-identical sampling in presence of stragglers

Author name not available (Why is that?)

Publication date: 25 August 2021

Abstract: We consider decentralized consensus optimization when workers sample data from non-identical distributions and perform variable amounts of work due to slow nodes known as stragglers. The problem of non-identical distributions and the problem of variable amount of work have been previously studied separately. In our work we analyze them together under a unified system model. We study the convergence of the optimization algorithm when combining worker outputs under two heuristic methods: (1) weighting equally, and (2) weighting by the amount of work completed by each. We prove convergence of the two methods under perfect consensus, assuming straggler statistics are independent and identical across all workers for all iterations. Our numerical results show that under approximate consensus the second method outperforms the first method for both convex and non-convex objective functions. We make use of the theory on minimum variance unbiased estimator (MVUE) to evaluate the existence of an optimal method for combining worker outputs. While we conclude that neither of the two heuristic methods are optimal, we also show that an optimal method does not exist.

Has companion code repository: https://github.com/thadikari/consensus

This page was built for publication: Decentralized optimization with non-identical sampling in presence of stragglers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6375969)