TY - GEN
T1 - Efficient learning by consensus over regular networks
AU - Weng, Zhiyuan
AU - Djurić, Petar M.
PY - 2014
Y1 - 2014
N2 - In a network, each agent communicates with its neighbors. All the agents have initial observations, and they update their beliefs with the average of the beliefs in their neighborhoods. It is well known that in the long run, the network will reach consensus. However, the agents do not necessarily converge to the global average of the initial observations of all the agents in the network. Instead, the result is always a weighted average. Moreover, it takes infinite time for the process to converge. In this paper, we address regular networks of agents, where each agent (node) has the same number of agents. We propose a method that allows agents in these networks to learn the global average using the history of its local average in finite time.
AB - In a network, each agent communicates with its neighbors. All the agents have initial observations, and they update their beliefs with the average of the beliefs in their neighborhoods. It is well known that in the long run, the network will reach consensus. However, the agents do not necessarily converge to the global average of the initial observations of all the agents in the network. Instead, the result is always a weighted average. Moreover, it takes infinite time for the process to converge. In this paper, we address regular networks of agents, where each agent (node) has the same number of agents. We propose a method that allows agents in these networks to learn the global average using the history of its local average in finite time.
KW - Consensus
KW - efficient learning
KW - learning in agent networks
KW - regular graphs
UR - https://www.scopus.com/pages/publications/84905270299
U2 - 10.1109/ICASSP.2014.6855008
DO - 10.1109/ICASSP.2014.6855008
M3 - Conference contribution
SN - 9781479928927
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 7253
EP - 7257
BT - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Y2 - 4 May 2014 through 9 May 2014
ER -