Improved Vapnik Cervonenkis bounds
Olivier Catoni
Abstract
We give a new proof of VC bounds where we avoid the use of symmetrization and use a shadow sample of arbitrary size. We also improve on the variance term. This results in better constants, as shown on numerical examples. Moreover our bounds still hold for non identically distributed independent random variables. Keywords: Statistical learning theory, PAC-Bayesian theorems, VC dimension.
Create a lesson
Related papers
Instance-Optimal Adaptive Location Estimation via Multiscale Mid-Summaries
Qiaosen Wang, Chao Gao
Robust Multi-Task Learning for Principal Component Analysis
Dali Liu, Haolei Weng
Principal component error in high-dimensional factor models
Alex Bernstein, Lisa R. Goldberg, Nicholas Gunther et al.
Approximation Theorems for High-Dimensional Canonical U-Statistics: Gaussian Chaos and Phase Transition
Leheng Cai, Qirui Hu
On the parametric and semiparametric Fisher information matrix for non-zero mean stationary spherical invariant random processes
Jean-Pierre Delmas, Habti Abeida, Stefano Fortunati
Inference for two-stage sampling in spatial surveys
Guillaume Chauvet, Olivier Bouriaud, Trinh H. K. Duong