Authors: Jialei Wang (Two Sigma), Blake Woodworth, Adam Smith, Brendan McMahan, Nathan Sebro
To be presented at: 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada
Abstract: We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive lower bounds for several specific parallel optimization settings, including delayed updates and parallel processing with intermittent communication. We highlight gaps between lower and upper bounds on the oracle complexity, and cases where the “natural” algorithms are not known to be optimal.
