Minimum-norm interpolants in reproducing kernel Hilbert spaces have risk that can exhibit multiple peaks and valleys as the sample size grows, with peak locations predicted by the scaling d = n^α.
Does data interpolation contradict statistical optimality?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
fields
math.ST 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels
Minimum-norm interpolants in reproducing kernel Hilbert spaces have risk that can exhibit multiple peaks and valleys as the sample size grows, with peak locations predicted by the scaling d = n^α.