Information-theoretic lower bounds on Bayes risk in decentralized estimation

Aolin Xu, Maxim Raginsky

Research output: Contribution to journalArticlepeer-review


We derive lower bounds on the Bayes risk in decentralized estimation, where the estimator does not have direct access to the random samples generated conditionally on the random parameter of interest, but only to the data received from local processors that observe the samples. The received data are subject to communication constraints due to the quantization and the noisy communication channels from the processors to the estimator. We first derive general lower bounds on the Bayes risk using information-theoretic quantities, such as mutual information, information density, small ball probability, and differential entropy. We then apply these lower bounds to the decentralized case, using strong data processing inequalities to quantify the contraction of information due to communication constraints. We treat the cases of a single processor and of multiple processors, where the samples observed by different processors may be conditionally dependent given the parameter, for noninteractive and interactive communication protocols. Our results recover and improve recent lower bounds on the Bayes risk and the minimax risk for certain decentralized estimation problems, where previously only conditionally independent sample sets and noiseless channels have been considered. Moreover, our results provide a general way to quantify the degradation of estimation performance caused by distributing resources to multiple processors, which is only discussed for specific examples in existing works.

Original languageEnglish (US)
Article number7801953
Pages (from-to)1580-1600
Number of pages21
JournalIEEE Transactions on Information Theory
Issue number3
StatePublished - Mar 2017


  • Bayes risk
  • Decentralized estimation
  • Neyman-Pearson converse
  • Small ball probability
  • Strong data processing inequalities

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences


Dive into the research topics of 'Information-theoretic lower bounds on Bayes risk in decentralized estimation'. Together they form a unique fingerprint.

Cite this