Spotlight
McDiarmid-Type Inequalities for Graph-Dependent Variables and Stability Bounds
Rui (Ray) Zhang · Xingwu Liu · Yuyi Wang · Liwei Wang

Wed Dec 11th 04:50 -- 04:55 PM @ West Ballroom C
in Track 4 Session 4 »

A crucial assumption in most statistical learning theory is that samples are independently and identically distributed (i.i.d.). However, for many real applications, the i.i.d. assumption does not hold. We consider learning problems in which examples are dependent and their dependency relation is characterized by a graph. To establish algorithm-dependent generalization theory for learning with non-i.i.d. data, we first prove novel McDiarmid-type concentration inequalities for Lipschitz functions of graph-dependent random variables. We show that concentration relies on the forest complexity of the graph, which characterizes the strength of the dependency. We demonstrate that for many types of dependent data, the forest complexity is small and thus implies good concentration. Based on our new inequalities we are able to build stability bounds for learning from graph-dependent data.

Author Information

Rui (Ray) Zhang (School of Mathematics, Monash University)
Xingwu Liu (University of Chinese Academy of Sciences)
Yuyi Wang (ETH Zurich)
Liwei Wang (Peking University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors