This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
27th International Conference on Distributed Computing Systems (ICDCS '07)
Distributed Density Estimation Using Non-parametric Statistics
Toronto, Canada
June 25-June 27
ISBN: 0-7695-2837-3
Yusuo Hu, Microsoft Research Asia, China
Hua Chen, Tsinghua University
Jian-guang Lou, Microsoft Research Asia, China
Jiang Li, Microsoft Research Asia, China
Learning the underlying model from distributed data is often useful for many distributed systems. In this paper, we study the problem of learning a non-parametric model from distributed observations. We propose a gossip-based distributed kernel density estimation algorithm and analyze the convergence and consistency of the estimation process. Furthermore, we extend our algorithm to distributed systems under communication and storage constraints by introducing a fast and efficient data reduction algorithm. Experiments show that our algorithm can estimate underlying density distribution accurately and robustly with only small communication and storage overhead.
Index Terms:
Kernel Density Estimation, Non-parametric Statistics, Distributed Estimation, Data Reduction, Gossip
Citation:
Yusuo Hu, Hua Chen, Jian-guang Lou, Jiang Li, "Distributed Density Estimation Using Non-parametric Statistics," icdcs, pp.28, 27th International Conference on Distributed Computing Systems (ICDCS '07), 2007
Usage of this product signifies your acceptance of the Terms of Use.