Distributed Stochastic Gradient Tracking Methods
Preprint
Abstract
In this paper, we study the problem of distributed multi-agent optimization over a network, where each agent possesses a local cost function that is smooth and strongly convex. The global objective is to find a common solution that minimizes the average of all cost functions. Assuming agents only have access to unbiased estimates of the gradients of their local cost functions, we consider a distributed stochastic gradient tracking method (DSGT) and a gossip-like stochastic gradient tracking method (GSGT). We show that, in expectation, the iterates generated by each agent are attracted to a neighborhood of the optimal solution, where they accumulate exponentially fast (under a constant stepsize choice). Under DSGT, the limiting (expected) error bounds on the distance of the iterates from the optimal solution decrease with the network size $n$, which is a comparable performance to a centralized stochastic gradient algorithm. Moreover, we show that when the network is well-connected, GSGT incurs lower communication cost than DSGT while maintaining a similar computational cost. Numerical example further demonstrates the effectiveness of the proposed methods.
Keywords
All Related Versions
This publication has 45 references indexed in Scilit:
- Communication-efficient algorithms for decentralized and stochastic optimizationMathematical Programming, 2018
- Convergence Rates for Distributed Stochastic Optimization Over Random Networks2018
- Network Topology and Communication-Computation Tradeoffs in Decentralized OptimizationProceedings of the IEEE, 2018
- Distributed convex optimization via continuous-time coordination algorithms with discrete-time communicationAutomatica, 2015
- An augmented Lagrangian method for distributed optimizationMathematical Programming, 2014
- Distributed multi-agent optimization with state-dependent communicationMathematical Programming, 2011
- Distributed Asynchronous Constrained Stochastic OptimizationIEEE Journal of Selected Topics in Signal Processing, 2011
- Distributed Stochastic Subgradient Projection Algorithms for Convex OptimizationJournal of Optimization Theory and Applications, 2010
- Multi-fidelity optimization via surrogate modellingProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2007
- Stochastic Approximation and Recursive Algorithms and Applications2003