Rademacher processes and bounding the risk of function learning
Vladimir Koltchinskii, Dmitry Panchenko
Abstract
We construct data dependent bounds on the risk in function learning problems. The bounds are based on the local norms of the Rademacher process indexed by the underlying function class and they do not require prior knowledge about the distribution of the training examples or any specific properties of the function class.
Create a lesson
Related papers
Sublinear multi-type preferential attachment
Anna Ben-Hamou, Nicolas Broutin, Camille Cazaux
Uniform Central Limit Theorems for Degree Distributions of Sparse Graphon Models
Robert Lunde, Soumendra Lahiri
Matching Random Point Sets with Minimum Distortion
Itai Benjamini, Mark Braverman, Elad Tzalik et al.
Uniqueness and full coverage in k-neighbor graphs
David Coupier, Benoît Henry, Benedikt Jahnel et al.
Bass martingales need not stretch
Mathias Beiglböck, Manuel Hasenbichler, Gudmund Pammer
Universality of smallest singular values of random row submatrices and phase retrieval problems
Shu Wen, Christian E. Häggblom, Xiufan Yang