Non-Convex Distributed Optimization
Preprint
Abstract
We study distributed non-convex optimization on a time-varying multi-agent network. Each node has access to its own smooth local cost function, and the collective goal is to minimize the sum of these functions. We generalize the results obtained previously to the case of non-convex functions. Under some additional technical assumptions on the gradients we prove the convergence of the distributed push-sum algorithm to some critical point of the objective function. By utilizing perturbations on the update process, we show the almost sure convergence of the perturbed dynamics to a local minimum of the global objective function. Our analysis shows that this noised procedure converges at a rate of $O(1/t)$.
Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Distributed Optimization Over Time-Varying Directed GraphsIEEE Transactions on Automatic Control, 2014
- A Model-Free Approach to Wind Farm Control Using Game Theoretic MethodsIEEE Transactions on Control Systems Technology, 2013
- An Approximate Dual Subgradient Algorithm for Multi-Agent Non-Convex OptimizationIEEE Transactions on Automatic Control, 2012
- Distributed multi-agent optimization with state-dependent communicationMathematical Programming, 2011
- Distributed Subgradient Methods for Convex Optimization Over Random NetworksIEEE Transactions on Automatic Control, 2010
- Distributed Stochastic Subgradient Projection Algorithms for Convex OptimizationJournal of Optimization Theory and Applications, 2010
- Distributed Non-Autonomous Power Control through Distributed Convex Optimization2009
- Distributed Subgradient Methods for Multi-Agent OptimizationIEEE Transactions on Automatic Control, 2009
- Gossip-based computation of aggregate information2004
- Distributed asynchronous deterministic and stochastic gradient optimization algorithmsIEEE Transactions on Automatic Control, 1986