Distributed learning based on the divide and conquer approach is a powerful tool for big data processing. We introduce a distributed kernel gradient descent algorithm for the minimum error entropy principle and analyze its convergence. We show that the $L^2$ error decays at a minimax optimal rate under some mild conditions. As a tool we establish some concentration inequalities for U-statistics which play pivotal roles in our error analysis.

中文翻译：

---

最小误差熵原理的分布式核梯度下降算法

基于分而治之方法的分布式学习是大数据处理的强大工具。针对最小误差熵原理，介绍了一种分布式核梯度下降算法，并对其收敛性进行了分析。我们表明${\mathrm{大号}}^2$在某些温和条件下，误差以最小最大最佳速率衰减。作为一种工具，我们为U统计建立了一些集中不等式，这些不等式在我们的误差分析中起着关键作用。