Does data interpolation contradict statistical optimality?
We show that learning methods interpolating the training data can achieve optimal rates for the problems of nonparametric regression and prediction with square loss.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionregressionSimilar Papers 제목 키워드 기반
Projective view at Optimization Problem for Multiband Filter
The best uniform rational approximation of the \emph{sign} function on two intervals separated by zero was explicitly solved by E.I. Zolotar\"ev in 1877. This optimization problem is the initial step in the staircase of …
Electrical EngineeringBenefit of Interpolation in Nearest Neighbor Algorithms
In some studies \citep[e.g.,][]{zhang2016understanding} of deep learning, it is observed that over-parametrized deep neural networks achieve a small testing error even when the training error is almost zero. Despite nume…
On Optimal Interpolation In Linear Regression
Understanding when and why interpolating methods generalize well has recently been a topic of interest in statistical learning theory. However, systematically connecting interpolating methods to achievable notions of opt…
Learning TheoryregressionThe Optimality of Kernel Classifiers in Sobolev Space
Kernel methods are widely used in machine learning, especially for classification problems. However, the theoretical analysis of kernel classification is still limited. This paper investigates the statistical performance…
ClassificationInterpolation of numerical series by the Fermat-Torricelli point construction method on the example of the numerical series of inflation in the Czech Republic in 2011-2021
The use of regression analysis for processing experimental data is fraught with certain difficulties, which, when models are constructed, are associated with assumptions, and there is a normal law of error distribution a…
regression