Learning Theory: An Approximation Theory Viewpoint: Least squares regularization

77 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

On integral probability metrics, φ-divergences and binary classification (2009, background): “See Cucker and Zhou [50, Chapter 5] for the estimates of entropy numbers for various H .”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “alization bounds from statistical learning theory [133], [134] and the connection between regularization and effective hypothesis space [135].”
Analysis of Kernel Mean Matching under Covariate Shift (2012, background): “…on the regression function that we borrow from learning theory (Cucker & Zhou, 2007), the convergence rate, proved in Theorem 2, degrades gracefully to O(n − θ 2(θ+2) tr +n − θ 2(θ+2) te ), where θ > 0 is a smoothness parameter measuring certain regularity of the regression function (in…”