-
A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization
This paper addresses consensus optimization problem in a multi-agent net...
read it
-
Decentralized Consensus Optimization Based on Parallel Random Walk
The alternating direction method of multipliers (ADMM) has recently been...
read it
-
Private Weighted Random Walk Stochastic Gradient Descent
We consider a decentralized learning setting in which data is distribute...
read it
-
Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
We consider the problem of fully decentralized multi-agent reinforcement...
read it
-
Privacy-preserving Incremental ADMM for Decentralized Consensus Optimization
The alternating direction method of multipliers (ADMM) has been recently...
read it
-
Pooling or Sampling: Collective Dynamics for Electrical Flow Estimation
The computation of electrical flows is a crucial primitive for many rece...
read it
-
Rollout Sampling Policy Iteration for Decentralized POMDPs
We present decentralized rollout sampling policy iteration (DecRSPI) - a...
read it
Walkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization
This paper addresses consensus optimization problems in a multi-agent network, where all agents collaboratively find a minimizer for the sum of their private functions. We develop a new decentralized algorithm in which each agent communicates only with its neighbors. State-of-the-art decentralized algorithms use communications between either all pairs of adjacent agents or a random subset of them at each iteration. Another class of algorithms uses a random walk incremental strategy, which sequentially activates a succession of nodes; these incremental algorithms require diminishing step sizes to converge to the solution, so their convergence is relatively slow. In this work, we propose a random walk algorithm that uses a fixed step size and converges faster than the existing random walk incremental algorithms. Our algorithm is also communication efficient. Each iteration uses only one link to communicate the latest information for an agent to another. Since this communication rule mimics a man walking around the network, we call our new algorithm Walkman. We establish convergence for convex and nonconvex objectives. For decentralized least squares, we derive a linear rate of convergence and obtain a better communication complexity than those of other decentralized algorithms. Numerical experiments verify our analysis results.
READ FULL TEXT
Comments
There are no comments yet.