Beyond Ridge Regression for Distribution-Free Data. (arXiv:2206.08757v1 [cs.LG])

In supervised batch learning, the predictive normalized maximum likelihood
(pNML) has been proposed as the min-max regret solution for the
distribution-free setting, where no distributional assumptions are made on the
data. However, the pNML is not defined for a large capacity hypothesis class as
over-parameterized linear regression. For a large class, a common approach is
to use regularization or a model prior. In the context of online prediction
where the min-max solution is the Normalized Maximum Likelihood (NML), it has …

arxiv data distribution free lg regression ridge