pith. sign in

arxiv: 1806.09471 · v1 · pith:HKECSENNnew · submitted 2018-06-25 · 📊 stat.ML · cs.LG· math.ST· stat.TH

Does data interpolation contradict statistical optimality?

classification 📊 stat.ML cs.LGmath.STstat.TH
keywords dataachievecontradictinterpolatinginterpolationlearninglossmethods
0
0 comments X
read the original abstract

We show that learning methods interpolating the training data can achieve optimal rates for the problems of nonparametric regression and prediction with square loss.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.