In this paper, we consider a stochastic distributed nonconvex optimization problem with the cost function being over n agents having access only to zeroth-order (ZO) information of cost. This has various machine learning applications. As solution, propose two ZO algorithms, in which at each iteration agent samples local oracle points time-varying smoothing parameter. We show that proposed algor...

Distributed multi-agent optimization finds many applications in distributed learning, control, estimation, etc. Most existing algorithms assume knowledge of first-order information the objective and have been analyzed for convex problems. However, there are situations where is nonconvex, one can only evaluate function values at finitely points. In this paper we consider derivative-free nonconve...

At COLING80, we reported on an Interactive Translation System called ITS. We will discuss t h r ee p rob lems in the design of the first version of ITS: (1) human f ac to r s , (2) the "all or noth ing" syndrome, and (3) traditional centralized processing. We will also discuss a new vers ion of ITS, which is now being programmed. This new vers ion will hopeful ly o v e r c o m e these p rob lem...

We survey applications of the theory of partial orders to distributed computing. A distributed computation is a poset on the set of events based on the observable happened-before relation. Online chain decomposition of posets has applications in timestamping events with vectors such that the vectors preserve the partial order. The lower bounds on the dimension of these vectors use the dimension...

This thesis provides a systematic framework for the development and analysis of distributed optimization methods for multi-agent networks with time-varying connectivity. The goal is to optimize a global objective function which is the sum of local objective functions privately known to individual agents. In our methods, each agent iteratively updates its estimate of the global optimum by optimi...

-The burgeoning amount of textual data in distributed sources combined with the obstacles involved in creating and maintaining central repositories motivates the need for effective distributed information extraction and mining techniques. Recently, as the need to mine patterns across distributed databases has grown, Distributed Association Rule Mining (D-ARM) algorithms have been developed. The...

In this paper, we derive the impulse response of the distributed order integrator/ differentiator and its asymptotic property by using the complex path integral. Based on the derived analytical impulse response, we present a technique to perform the discretization of the above distributed order integrator/differentiator. The derived asymptotic property can be applied to verify the feasibility o...