Communication Efficient Coresets for Empirical Loss Minimization
UAI, pp. 752-761, 2015.
In this paper, we study the problem of empirical loss minimization with l2-regularization in distributed settings with significant communication cost. Stochastic gradient descent (SGD) and its variants are popular techniques for solving these problems in large-scale applications. However, the communication cost of these techniques is usua...More
Full Text (Upload PDF)