Timezone: »

 
Poster
Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
Blake Woodworth · Jialei Wang · Adam Smith · Brendan McMahan · Nati Srebro

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 210 #11
in Thu Poster Session B »

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.

Keywords: Learning Theory · Convex Optimization · Stochastic Methods
[ Paper] 

Author Information

Blake Woodworth (TTI-Chicago)
Jialei Wang (Two Sigma Investments, University of Chicago)
Adam Smith (Boston University)
Brendan McMahan (Google)
Nati Srebro (TTI-Chicago)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors