Complexity regularization via localized random penalties
Gabor Lugosi, Marten Wegkamp
Abstract
In this article, model selection via penalized empirical loss minimization in nonparametric classification problems is studied. Data-dependent penalties are constructed, which are based on estimates of the complexity of a small subclass of each model class, containing only those functions with small empirical loss. The penalties are novel since those considered in the literature are typically based on the entire model class. Oracle inequalities using these penalties are established, and the advantage of the new penalties over those based on the complexity of the whole model class is demonstrated.
Create a lesson
Related papers
Minimax signal detection in regression under differential privacy
Elly K. H. Hung
A Tetration Distribution
Micah Thornton
Multi-modal Laplace-based sampling
Maxime Egéa, Hanyue Gu, Daniel Rudolf et al.
Studentized inference in randomized experiments when a few units dominate the outcome variation
Xinyuan Chen, Jonathan W. Kiesel, Jonathan R. Woody
Nonparametric Intensity Estimation for Covariate-Driven Poisson Processes Using Deep Learning
Atsutomo Yara, Yoshikazu Terada
Specification LASSO and a Flexible Characteristics-Based Asset Pricing Model
Chaohua Dong, Shuyi Ge, Shaoran Li et al.