One-shot Distributed Algorithm for Generalized Eigenvalue Problem
This addresses a bottleneck in distributed high-dimensional statistics for data privacy and storage, but it is incremental as it modifies existing methods for specific cases like repeated eigenvalues.
The authors tackled the distributed generalized eigenvalue problem (GEP) by proposing a one-shot communication framework, achieving effectiveness in numerical experiments with theoretical error analysis.
Nowadays, more and more datasets are stored in a distributed way for the sake of memory storage or data privacy. The generalized eigenvalue problem (GEP) plays a vital role in a large family of high-dimensional statistical models. However, the existing distributed method for eigenvalue decomposition cannot be applied in GEP for the divergence of the empirical covariance matrix. Here we propose a general distributed GEP framework with one-shot communication for GEP. If the symmetric data covariance has repeated eigenvalues, e.g., in canonical component analysis, we further modify the method for better convergence. The theoretical analysis on approximation error is conducted and the relation to the divergence of the data covariance, the eigenvalues of the empirical data covariance, and the number of local servers is analyzed. Numerical experiments also show the effectiveness of the proposed algorithms.