Communication-Efficient Distributed Strongly Convex Stochastic Optimization: Non-Asymptotic Rates

We examine fundamental tradeoffs in iterative distributed zeroth and first order stochastic optimization in multi-agent networks in terms of communication cost (number of per-node transmissions) and computational cost, measured by the number of per-node noisy function (respectively, gradient) evaluations with zeroth order (respectively, first order) methods. Specifically, we develop novel distributed stochastic optimization methods for zeroth and first order strongly convex optimization by utilizing a probabilistic inter-agent communication protocol that increasingly sparsifies communications among agents as time progresses. Under standard assumptions on the cost functions and the noise statistics, we establish with the proposed method the O(1/(Ccomm)4/3-zeta) and O(1/(Ccomm)8/9-zeta) mean square error convergence rates, for the first and zeroth order optimization, respectively, where Ccomm is the expected number of network communications and zeta>0 is arbitrarily small. The methods are shown to achieve order-optimal convergence rates in terms of computational cost~Ccomp, O(1/Ccomp) (first order optimization) and O(1/(Ccomp)2/3) (zeroth order optimization), while achieving the order-optimal convergence rates in terms of iterations. Experiments on real-life datasets illustrate the efficacy of the proposed algorithms.