Abstract：In modern massive data modelling, distributed learning plays a critical role in enhance scalability, efficiency and privacy protection. Heterogeneity and robustness of a distributed learning algorithm are key aspects related to the accuracy and reliability of learning result.

In this work, under the common framework of statistical learning, we propose the convex hull search algorithm which has four main advantages: fast convergence, high accuracy, adjustable robustness and tunning friendly. The corresponding convergence and asymptotic normality result for CHS algorithm are established which show its adaptability on data heterogeneity. We exemplify our algorithm on regression and clustering tasks through synthetic data. Furthermore, a real energy consumption data is implemented for Gaussian process regression hyperparameters optimization. Existing numerical result confirm our superiority and exhibit wide applicability of our algorithm.

报告人简介：

陈钊，复旦大学大数据学院青年研究员，博士生导师。2012年在中国科学技术大学获得博士学位。之后在美国普林斯顿大学，宾夕法尼亚州立大学从事博士后研究及研究型助理教授工作。科研成果发表在AoS, JASA, JoE，Statistica Sinica, Energy and buildings等期刊上。主要研究方向：高维统计推断，稳健回归，时间序列，非参数及半参数统计方法，以及将统计方法应用于建筑能源，金融计量等领域。