On the Rademacher Complexity of Linear Hypothesis Sets [article]

Pranjal Awasthi, Natalie Frank, Mehryar Mohri
2020 arXiv   pre-print
Linear predictors form a rich class of hypotheses used in a variety of learning algorithms. We present a tight analysis of the empirical Rademacher complexity of the family of linear hypothesis classes with weight vectors bounded in ℓ_p-norm for any p ≥ 1. This provides a tight analysis of generalization using these hypothesis sets and helps derive sharp data-dependent learning guarantees. We give both upper and lower bounds on the Rademacher complexity of these families and show that our
more » ... improve upon or match existing bounds, which are known only for 1 ≤ p ≤ 2.
arXiv:2007.11045v1 fatcat:cbekymbumvddrcmlsx5zn4kvzq