Tightening the Sample Complexity of Empirical Risk Minimization via Preconditioned Stability
arXiv: Learning, Volume abs/1601.04011, 2016.
We tighten the sample complexity of empirical risk minimization (ERM) associated with a class of generalized linear models that include linear and logistic regression. In particular, we conclude that ERM attains the optimal sample complexity for linear regression. Our analysis relies on a new notion of stability, called preconditioned sta...More
PPT (Upload PPT)