Communication-efficient Algorithm for Distributed Sparse Learning via Two-way Truncation
This work addresses communication bottlenecks in distributed machine learning for high-dimensional sparse problems, offering an incremental improvement over existing methods.
The paper tackles the problem of high-dimensional distributed sparse learning by proposing a communication-efficient algorithm that reduces communication costs from constant times the dimension number to constant times the sparsity number, with theoretical guarantees matching centralized methods and experimental verification on simulated and real data.
We propose a communicationally and computationally efficient algorithm for high-dimensional distributed sparse learning. At each iteration, local machines compute the gradient on local data and the master machine solves one shifted $l_1$ regularized minimization problem. The communication cost is reduced from constant times of the dimension number for the state-of-the-art algorithm to constant times of the sparsity number via Two-way Truncation procedure. Theoretically, we prove that the estimation error of the proposed algorithm decreases exponentially and matches that of the centralized method under mild assumptions. Extensive experiments on both simulated data and real data verify that the proposed algorithm is efficient and has performance comparable with the centralized method on solving high-dimensional sparse learning problems.