Distributed Mean Estimation with Limited Communication.
ICML(2017)
摘要
Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for d dimensional data with n clients, a naive stochastic rounding approach yields a mean squared error (MSE) of Θ (d/n) and uses a constant number of bits per dimension per client. We then extend this naive algorithm in two ways: we show that applying a structured random rotation before quantization reduces the error to O((log d)/n) and a better coding strategy further reduces the error to O(1/n). We also show that the latter coding strategy is optimal up to a constant in the minimax sense i.e., it achieves the best MSE for a given communication cost. We finally demonstrate the practicality of our algorithms by applying them to distributed Lloydu0027s algorithm for k-means and power iteration for PCA.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络