Theoretical analysis of divide-and-conquer ERM: From the perspective of multi-view

Yun Liao, Yong Liu, Shizhong Liao, Qinghua Hu, Jianwu Dang

Abstract: Highlights•Present original learning theories for distributed learning from a multi-view perspective.•Derive and prove a first series of risk bounds of divide-and-conquer ERM in RKHS.•Explore the risk bounds among learning complexities and number of views under comprehensive conditions.