Alon Gonen, Shai Shalev-Shwartz
Published 2016-01-15Version 1
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 stability, which may be of independent interest.
Risk and parameter convergence of logistic regression
On the Stability of Empirical Risk Minimization in the Presence of Multiple Risk Minimizers
Nearly Optimal Sample Complexity of Offline KL-Regularized Contextual Bandits under Single-Policy Concentrability
![QR code for arXiv:1601.04011 [cs.LG]](http://oss.arxitics.com/images/favicon.svg)