Poster
Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
Blake Woodworth · Jialei Wang · Adam Smith · Brendan McMahan · Nati Srebro
Room 210 #11
Keywords: [ Learning Theory ] [ Convex Optimization ] [ Stochastic Methods ]
We suggest a general oracle-based framework that captures parallel stochastic optimization in different parallelization 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 to study 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.
Live content is unavailable. Log in and register to view live content