English

The Sample Complexity of Learning Linear Predictors with the Squared Loss

Machine Learning 2021-11-23 v3 Machine Learning

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.

Keywords

Cite

@article{arxiv.1406.5143,
  title  = {The Sample Complexity of Learning Linear Predictors with the Squared Loss},
  author = {Ohad Shamir},
  journal= {arXiv preprint arXiv:1406.5143},
  year   = {2021}
}

Comments

Revised discussion to clarify that the lower bound is currently not fully matched by algorithms which must return linear predictors

R2 v1 2026-06-22T04:42:37.647Z