Dimensionality Reduction, Regularization, and Generalization in Overparameterized Regressions

Authors:
  • NTNingyuan Teresa
    Ningyuan Teresa
  • DHDavid W. Hogg
    David W. Hogg
  • SVSoledad Villar
    Soledad Villar

Abstract
Overparameterization in deep learning is powerful: Very large models fit the training data perfectly and yet often generalize well. This realization brought back the study of linear models for regr...
Funding Information
  • European Office of Aerospace Research and Development (FA9550-18-1-7007)
  • NSF-Simons Resarch Collaboration on the Mathematical and Scientific Foundations of Deep Learning (DMS 2031985)
  • National Science Foundation (DMS 2044349)

This publication has 31 references indexed in Scilit: