Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization

Journal of Machine Learning Research, Volume 18, Issue 222, 2017, Pages 222:1-222:13.

Cited by: 13|Bibtex|Views9|Links
EI

Abstract:

We show that the average stability notion introduced by cite{kearns1999algorithmic, bousquet2002stability} is invariant to data preconditioning, for a wide class of generalized linear models that includes most of the known exp-concave losses. In other words, when analyzing the stability rate of a given algorithm, we may assume the optimal...More

Code:

Data:

Your rating :
0

 

Tags
Comments