Home
Speakers
Schedule
Location and Directions
Hotel Information
Lang Tong
Cornell University
Title: Energy Scaling Laws for Distributed Inference in Random Fusion Networks
Abstract: We examine the cost of data fusion in a random network for statistical inference. In particular, we are interested in scalable fusion policies that achieve optimal inference at the fusion center and have a constant average cost per sensor as the size of the network increases. We note that schemes based on multihop routing are in general not scalable. For statistical inference involving random dependency graphs, the key to scalable data fusion is in-network processing that exploits structures of statistical correlations.