Corpus ID: 219558817

On Uniform Convergence and Low-Norm Interpolation Learning

  title={On Uniform Convergence and Low-Norm Interpolation Learning},
  author={Lijia Zhou and Dougal J. Sutherland and Nathan Srebro},
  • Lijia Zhou, Dougal J. Sutherland, Nathan Srebro
  • Published 2020
  • Mathematics, Computer Science
  • ArXiv
  • We consider an underdetermined noisy linear regression model where the minimum-norm interpolating predictor is known to be consistent, and ask: can uniform convergence in a norm ball, or at least (following Nagarajan and Kolter) the subset of a norm ball that the algorithm selects on a typical input set, explain this success? We show that uniformly bounding the difference between empirical and population errors cannot show any learning in the norm ball, and cannot show consistency for any set… CONTINUE READING

    Topics from this paper.


    Publications referenced by this paper.