Communication complexity of estimating correlations

Uri Hadar*, Jingbo Liu, Yury Polyanskiy, Ofer Shayevitz

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations


We characterize the communication complexity of the following distributed estimation problem. Alice and Bob observe infinitely many iid copies of ρ-correlated unit-variance (Gaussian or ±1 binary) random variables, with unknown ρ ∈ [−1, 1]. By interactively exchanging k bits, Bob wants to produce an estimate ρ of ρ. We show that the best possible performance (optimized over interaction protocol Π and estimator ρ) satisfies infΠρ supρ E[|ρ − ρ|2] = k−1(2 ln12 +o(1)). Curiously, the number of samples in our achievability scheme is exponential in k; by contrast, a naive scheme exchanging k samples achieves the same Ω(1/k) rate but with a suboptimal prefactor. Our protocol achieving optimal performance is one-way (non-interactive). We also prove the Ω(1/k) bound even when ρ is restricted to any small open sub-interval of [−1, 1] (i.e. a local minimax lower bound). Our proof techniques rely on symmetric strong data-processing inequalities and various tensorization techniques from information-theoretic interactive common-randomness extraction. Our results also imply an Ω(n) lower bound on the information complexity of the Gap-Hamming problem, for which we show a direct information-theoretic proof.

Original languageEnglish
Title of host publicationSTOC 2019 - Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing
EditorsMoses Charikar, Edith Cohen
PublisherAssociation for Computing Machinery
Number of pages12
ISBN (Electronic)9781450367059
StatePublished - 23 Jun 2019
Event51st Annual ACM SIGACT Symposium on Theory of Computing, STOC 2019 - Phoenix, United States
Duration: 23 Jun 201926 Jun 2019

Publication series

NameProceedings of the Annual ACM Symposium on Theory of Computing
ISSN (Print)0737-8017


Conference51st Annual ACM SIGACT Symposium on Theory of Computing, STOC 2019
Country/TerritoryUnited States


  • Communication complexity
  • Correlation estimation
  • Distributed estimation


Dive into the research topics of 'Communication complexity of estimating correlations'. Together they form a unique fingerprint.

Cite this