Abstract | ||
---|---|---|
This work presents and studies a distributed algorithm for solving optimization problems over networks where agents have individual costs to minimize subject to subspace constraints that require the minimizers across the network to lie in a low-dimensional subspace. The algorithm consists of two steps: i) a self-learning step where each agent minimizes its own cost using a stochastic gradient update; ii) and a social-learning step where each agent combines the updated estimates from its neighbors using the entries of a combination matrix that converges in the limit to the projection onto the low-dimensional subspace. We obtain analytical formulas that reveal how the step-size, data statistical properties, gradient noise, and subspace constraints influence the network mean-square-error performance. The results also show that in the small step-size regime, the iterates generated by the distributed algorithm achieve the centralized steady-state MSE performance. We provide simulations to illustrate the theoretical findings. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/IEEECONF44664.2019.9049074 | 2019 53rd Asilomar Conference on Signals, Systems, and Computers |
Keywords | DocType | ISSN |
low-dimensional subspace,subspace constraints,network mean-square-error performance,step-size regime,distributed algorithm,optimization problems,minimizers,stochastic gradient update,distributed learning,self-learning,social-learning,data statistical properties,gradient noise,steady-state MSE performance | Conference | 1058-6393 |
ISBN | Citations | PageRank |
978-1-7281-4301-9 | 0 | 0.34 |
References | Authors | |
22 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Roula Nassif | 1 | 57 | 6.89 |
Stefan Vlaski | 2 | 23 | 11.39 |
Ali H. Sayed | 3 | 9134 | 667.71 |