Optimal high-dimensional and nonparametric distributed testing under communication constraints
From MaRDI portal
Publication:6136575
Abstract: We derive minimax testing errors in a distributed framework where the data is split over multiple machines and their communication to a central machine is limited to bits. We investigate both the - and infinite-dimensional signal detection problem under Gaussian white noise. We also derive distributed testing algorithms reaching the theoretical lower bounds. Our results show that distributed testing is subject to fundamentally different phenomena that are not observed in distributed estimation. Among our findings, we show that testing protocols that have access to shared randomness can perform strictly better in some regimes than those that do not. We also observe that consistent nonparametric distributed testing is always possible, even with as little as -bit of communication and the corresponding test outperforms the best local test using only the information available at a single local machine. Furthermore, we also derive adaptive nonparametric distributed testing strategies and the corresponding theoretical lower bounds.
Recommendations
- Distributed nonparametric function estimation: optimal rate of convergence and cost of adaptation
- Communication lower bounds for statistical estimation problems via a distributed data processing inequality
- scientific article; zbMATH DE number 7306916
- Nonparametric distributed learning under general designs
- Adaptive distributed methods under communication constraints
Cites work
- scientific article; zbMATH DE number 7306916 (Why is no real title available?)
- Adaptive distributed methods under communication constraints
- Adaptive hypothesis testing using wavelets
- Best constants in Young's inequality, its converse, and its generalization to more than three functions
- Communication Complexity
- Communication lower bounds for statistical estimation problems via a distributed data processing inequality
- Decentralized Hypothesis Testing in Energy Harvesting Wireless Sensor Networks
- Decentralized detection by a large number of sensors
- Distributed adaptive Gaussian mean estimation with unknown variance: interactive protocol helps adaptation
- Distributed function estimation: adaptation using minimal communication
- Distributed nonparametric function estimation: optimal rate of convergence and cost of adaptation
- Gaussian kernels have only Gaussian maximizers
- High-dimensional probability. An introduction with applications in data science
- Hypothesis testing for densities and high-dimensional multinomials: sharp local minimax rates
- Hypothesis testing with communication constraints
- Inference Under Information Constraints I: Lower Bounds From Chi-Square Contraction
- Inference Under Information Constraints II: Communication Constraints and Shared Randomness
- Information-Theoretic Lower Bounds on Bayes Risk in Decentralized Estimation
- Nonparametric goodness-of-fit testing under Gaussian models
- Optimal Distributed Composite Testing in High-Dimensional Gaussian Models With 1-Bit Communication
- Statistical inference under multiterminal data compression
- Subadditivity of the entropy and its relation to Brascamp-Lieb type inequalities
- The Brascamp-Lieb inequalities: Finiteness, structure and extremals
This page was built for publication: Optimal high-dimensional and nonparametric distributed testing under communication constraints
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6136575)
