Vector Space Projections: A Numerical Approach to Signal and Image Processing, Neural Nets, and Optics
If multi-agent learning is the answer, what is the question?
Artificial Intelligence
Multiagent learning is not the answer. It is the question
Artificial Intelligence
Multi-agent learning for engineers
Artificial Intelligence
A Convergent Incremental Gradient Method with a Constant Step Size
SIAM Journal on Optimization
Sensing-based shape formation on modular multi-robot systems: a theoretical study
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Learning in diffusion networks with an adaptive projected subgradient method
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Broadcast gossip algorithms for consensus
IEEE Transactions on Signal Processing
An adaptive projected subgradient approach to learning in diffusion networks
IEEE Transactions on Signal Processing
IEEE Transactions on Signal Processing
Energy-based sensor network source localization via projection onto convex sets
IEEE Transactions on Signal Processing
Consensus acceleration in multiagent systems with the Chebyshev semi-iterative method
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Hi-index | 0.01 |
Many applications in multiagent learning are essentially convex optimization problems in which agents have only limited communication and partial information about the function being minimized (examples of such applications include, among others, coordinated source localization, distributed adaptive filtering, control, and coordination). Given this observation, we propose a new non-hierarchical decentralized algorithm for the asymptotic minimization of possibly time-varying convex functions. In our method each agent has knowledge of a time-varying local cost function, and the objective is to minimize asymptotically a global cost function defined by the sum of the local functions. At each iteration of our algorithm, agents improve their estimates of a minimizer of the global function by applying a particular version of the adaptive projected subgradient method to their local functions. Then the agents exchange and mix their improved estimates using a probabilistic model based on recent results in weighted average consensus algorithms. The resulting algorithm is provably optimal and reproduces as particular cases many existing algorithms (such as consensus algorithms and recent methods based on the adaptive projected subgradient method). To illustrate one possible application, we show how our algorithm can be applied to coordinated acoustic source localization in sensor networks.