Distributed asynchronous deterministic and stochastic gradient optimization algorithms
Reads0
Chats0
TLDR
A model for asynchronous distributed computation is presented and it is shown that natural asynchronous distributed versions of a large class of deterministic and stochastic gradient-like algorithms retain the desirable convergence properties of their centralized counterparts.Abstract:
We present a model for asynchronous distributed computation and then proceed to analyze the convergence of natural asynchronous distributed versions of a large class of deterministic and stochastic gradient-like algorithms. We show that such algorithms retain the desirable convergence properties of their centralized counterparts, provided that the time between consecutive interprocessor communications and the communication delays are not too large.read more
Citations
More filters
Book
Distributed Optimization and Statistical Learning Via the Alternating Direction Method of Multipliers
TL;DR: It is argued that the alternating direction method of multipliers is well suited to distributed convex optimization, and in particular to large-scale problems arising in statistics, machine learning, and related areas.
Journal ArticleDOI
Consensus and Cooperation in Networked Multi-Agent Systems
TL;DR: A theoretical framework for analysis of consensus algorithms for multi-agent networked systems with an emphasis on the role of directed information flow, robustness to changes in network topology due to link/node failures, time-delays, and performance guarantees is provided.
Journal ArticleDOI
Distributed Subgradient Methods for Multi-Agent Optimization
Angelia Nedic,Asuman Ozdaglar +1 more
TL;DR: The authors' convergence rate results explicitly characterize the tradeoff between a desired accuracy of the generated approximate optimal solutions and the number of iterations needed to achieve the accuracy.
Journal ArticleDOI
Stability of multiagent systems with time-dependent communication links
TL;DR: It is observed that more communication does not necessarily lead to faster convergence and may eventually even lead to a loss of convergence, even for the simple models discussed in the present paper.
Journal ArticleDOI
Coverage control for mobile sensing networks
TL;DR: In this paper, the authors describe decentralized control laws for the coordination of multiple vehicles performing spatially distributed tasks, which are based on a gradient descent scheme applied to a class of decentralized utility functions that encode optimal coverage and sensing policies.
References
More filters
Book
Theory and Practice of Recursive Identification
Lennart Ljung,Torsten Söderström +1 more
TL;DR: Methods of recursive identification deal with the problem of building mathematical models of signals and systems on-line, at the same time as data is being collected.
DissertationDOI
Problems in Decentralized Decision making and Computation.
TL;DR: A scheme whereby a set of decision makers (processors) exchange and update tentative decisions which minimize a common cost function, given information they possess is considered; it is shown that they are guaranteed to converge to consensus.
Journal ArticleDOI
Analysis of recursive stochastic algorithms
TL;DR: It is shown how a deterministic differential equation can be associated with the algorithm and examples of applications of the results to problems in identification and adaptive control.
Proceedings ArticleDOI
Some complexity questions related to distributive computing(Preliminary Report)
TL;DR: The quantity of interest, which measures the information exchange necessary for computing f, is the minimum number of bits exchanged in any algorithm.
Related Papers (5)
Coordination of groups of mobile autonomous agents using nearest neighbor rules
Ali Jadbabaie,Jie Lin,A.S. Morse +2 more