The Sample Complexity of Learning Linear Predictors with the Squared Loss
arXiv:1406.5143
Abstract
In this short note, we provide a sample complexity lower bound for learning linear predictors with respect to the squared loss. Our focus is on an agnostic setting, where no assumptions are made on the data distribution. This contrasts with standard results in the literature, which either make distributional assumptions, refer to specific parameter settings, or use other performance measures.
Revised discussion to clarify that the lower bound is currently not fully matched by algorithms which must return linear predictors