Sparse Normal Means Estimation with Sublinear Communication
share
We consider the problem of sparse normal means estimation in a distributed setting with communication constraints. We assume there are M machines, each holding a d-dimensional observation of a K-sparse vector μ corrupted by additive Gaussian noise. A central fusion machine is connected to the M machines in a star topology, and its goal is to estimate the vector μ with a low communication budget. Previous works have shown that to achieve the centralized minimax rate for the ℓ_2 risk, the total communication must be high - at least linear in the dimension d. This phenomenon occurs, however, at very weak signals. We show that once the signal-to-noise ratio (SNR) is slightly higher, the support of μ can be correctly recovered with much less communication. Specifically, we present two algorithms for the distributed sparse normal means problem, and prove that above a certain SNR threshold, with high probability, they recover the correct support with total communication that is sublinear in the dimension d. Furthermore, the communication decreases exponentially as a function of signal strength. If in addition KM≪ d, then with an additional round of sublinear communication, our algorithms achieve the centralized rate for the ℓ_2 risk. Finally, we present simulations that illustrate the performance of our algorithms in different parameter regimes.
READ FULL TEXT
