The Sample Complexity of Learning Linear Predictors with the Squared Loss
This work addresses a foundational gap in statistical learning theory for researchers, though it appears incremental as it builds on known lower bound techniques.
The paper tackles the problem of learning linear predictors with squared loss in an agnostic setting without distributional assumptions, providing a sample complexity lower bound that contrasts with existing literature.
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.