Communication complexity of convex optimization
From MaRDI portal
We consider a situation where each of two processors has access to a different convex function \(f_ i\), \(i=1,2\), defined on a common bounded domain. The processors are to exchange a number of binary messages, according to some protocol, until they find a point in the domain at which \(f_ 1+f_ 2\) is minimized, within some prespecified accuracy \(\epsilon\). Our objective is to determine protocols under which the number of exchanged messages is minimized.
Recommendations
- On the communication complexity of Lipschitzian optimization for the coordinated model of computation
- scientific article; zbMATH DE number 88975
- On communication complexity of vector-valued functions
- On the complexity of the exchange algorithm for minimax optimization problems
- On parallel complexity of nonsmooth convex optimization
Cites work
- Communication Complexity of Computing the Hamming Distance
- scientific article; zbMATH DE number 3858396 (Why is no real title available?)
- scientific article; zbMATH DE number 3688714 (Why is no real title available?)
- scientific article; zbMATH DE number 3790208 (Why is no real title available?)
- scientific article; zbMATH DE number 3793772 (Why is no real title available?)
- Lower Bounds on Information Transfer in Distributed Computations
- On the complexity of designing distributed protocols
Cited in
(5)- On the communication complexity of Lipschitzian optimization for the coordinated model of computation
- Optimal decisions in stochastic graphs with uncorrelated and correlated edge weights
- Nonconvex Optimization for Communication Networks
- Distributed Algorithmic Mechanism Design and Algebraic Communication Complexity
- Communication lower bounds using directional derivatives
This page was built for publication: Communication complexity of convex optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1100896)