### Abstract

We consider a distributed multi-agent network system where the goal is to minimize an objective function that can be written as the sum of component functions, each of which is known partially (with stochastic errors) to a specific network agent. We propose an asynchronous algorithm that is motivated by random gossip schemes where each agent has a local Poisson clock. At each tick of its local clock, the agent averages its estimate with a randomly chosen neighbor and adjusts the average using the gradient of its local function that is computed with stochastic errors.We investigate the convergence properties of the algorithm for two different classes of functions. First, we consider differentiable, but not necessarily convex functions, and prove that the gradients converge to zero with probability 1. Then, we consider convex, but not necessarily differentiable functions, and show that the iterates converge to an optimal solution almost surely.

Original language | English (US) |
---|---|

Title of host publication | Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009 |

Pages | 3581-3586 |

Number of pages | 6 |

DOIs | |

State | Published - Dec 1 2009 |

Externally published | Yes |

Event | 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009 - Shanghai, China Duration: Dec 15 2009 → Dec 18 2009 |

### Publication series

Name | Proceedings of the IEEE Conference on Decision and Control |
---|---|

ISSN (Print) | 0191-2216 |

### Other

Other | 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009 |
---|---|

Country | China |

City | Shanghai |

Period | 12/15/09 → 12/18/09 |

### ASJC Scopus subject areas

- Control and Systems Engineering
- Modeling and Simulation
- Control and Optimization

## Fingerprint Dive into the research topics of 'Asynchronous gossip algorithms for stochastic optimization'. Together they form a unique fingerprint.

## Cite this

*Proceedings of the 48th IEEE Conference on Decision and Control held jointly with 2009 28th Chinese Control Conference, CDC/CCC 2009*(pp. 3581-3586). [5399485] (Proceedings of the IEEE Conference on Decision and Control). https://doi.org/10.1109/CDC.2009.5399485