A theory of high dimensional regression with arbitrary correlations between input features and target functions: sample complexity, multiple descent curves and a hierarchy of phase transitions
Gabriel Mel, Surya Ganguli
International Conference on Machine Learning7/1/2021·Read paper
Abstract
https://proceedings.mlr.press/v139/mel21a.html
Make this part of your paper trail
Save this paper to a shelf, write a review, and keep your own notes.