paper-with-me

홈 › Papers

Oracle Inequalities for Convex Loss Functions with Non-Linear Targets

2013-12-12 · Mehmet Caner, Anders Bredahl Kock

This paper consider penalized empirical loss minimization of convex loss functions with unknown non-linear target functions. Using the elastic net penalty we establish a finite sample oracle inequality which bounds the loss of our estimator from above with high probability. If the unknown target is linear this inequality also provides an upper bound of the estimation error of the estimated parameter vector. These are new results and they generalize the econometrics and statistics literature. Next, we use the non-asymptotic results to show that the excess loss of our estimator is asymptotically of the same order as that of the oracle. If the target is linear we give sufficient conditions for consistency of the estimated parameter vector. Next, we briefly discuss how a thresholded version of our estimator can be used to perform consistent variable selection. We give two examples of loss functions covered by our framework and show how penalized nonparametric series estimation is contained as a special case and provide a finite sample upper bound on the mean square error of the elastic net series estimator.

📄 PDF Abstract BibTeX arXiv:1312.3525

Code (0)

등록된 구현이 없습니다.

Tasks

EconometricsVariable Selection

Similar Papers 제목 키워드 기반

Generalized Linear Models with Structured Sparsity Estimators

2021-04-29 · Mehmet Caner

In this paper, we introduce structured sparsity estimators in Generalized Linear Models. Structured sparsity estimators in the least squares loss are introduced by Stucky and van de Geer (2018) recently for fixed design …

regression

Asymptotic equivalence of regularization methods in thresholded parameter space

2016-05-11 · Yingying Fan, Jinchi Lv

High-dimensional data analysis has motivated a spectrum of regularization methods for variable selection and sparse modeling, with two popular classes of convex ones and concave ones. A long debate has been on whether on…

Variable Selection

High dimensional thresholded regression and shrinkage effect

2016-05-11 · Zemin Zheng, Yingying Fan, Jinchi Lv

High-dimensional sparse modeling via regularization provides a powerful tool for analyzing large-scale data sets and obtaining meaningful, interpretable models. The use of nonconvex penalty functions shows advantage in s…

PredictionregressionVariable SelectionVocal Bursts Intensity Prediction

Riemannian Projection-free Online Learning

2023-05-30 · NeurIPS 2023 11 · Zihao Hu, Guanghui Wang, Jacob Abernethy

The projection operation is a critical component in a wide range of optimization algorithms, such as online gradient descent (OGD), for enforcing constraints and achieving optimal regret bounds. However, it suffers from …

Parameter-free online learning via model selection

2017-12-30 · NeurIPS 2017 12 · Dylan J. Foster, Satyen Kale, Mehryar Mohri, Karthik Sridharan

We introduce an efficient algorithmic framework for model selection in online learning, also known as parameter-free online learning. Departing from previous work, which has focused on highly structured function classes …

modelModel Selection