paper-with-me

홈 › Papers

Model selection consistency from the perspective of generalization ability and VC theory with an application to Lasso

2016-06-01 · Ning Xu, Jian Hong, Timothy C. G. Fisher

Model selection is difficult to analyse yet theoretically and empirically important, especially for high-dimensional data analysis. Recently the least absolute shrinkage and selection operator (Lasso) has been applied in the statistical and econometric literature. Consis- tency of Lasso has been established under various conditions, some of which are difficult to verify in practice. In this paper, we study model selection from the perspective of generalization ability, under the framework of structural risk minimization (SRM) and Vapnik-Chervonenkis (VC) theory. The approach emphasizes the balance between the in-sample and out-of-sample fit, which can be achieved by using cross-validation to select a penalty on model complexity. We show that an exact relationship exists between the generalization ability of a model and model selection consistency. By implementing SRM and the VC inequality, we show that Lasso is L2-consistent for model selection under assumptions similar to those imposed on OLS. Furthermore, we derive a probabilistic bound for the distance between the penalized extremum estimator and the extremum estimator without penalty, which is dominated by overfitting. We also propose a new measurement of overfitting, GR2, based on generalization ability, that converges to zero if model selection is consistent. Using simulations, we demonstrate that the proposed CV-Lasso algorithm performs well in terms of model selection and overfitting control.

📄 PDF Abstract BibTeX arXiv:1606.00142

Code (0)

등록된 구현이 없습니다.

Tasks

Model Selection

Similar Papers 제목 키워드 기반

Stability and L2-penalty in Model Averaging

2023-11-23 · Hengkun Zhu, Guohua Zou

Model averaging has received much attention in the past two decades, which integrates available information by averaging over potential models. Although various model averaging methods have been developed, there are few …

Learning Theorymodel

Towards Understanding the Generalization of Graph Neural Networks

2023-05-14 · Huayi Tang, Yong liu

Graph neural networks (GNNs) are the most widely adopted model in graph-structured data oriented learning and representation. Despite their extraordinary success in real-world applications, understanding their working me…

Stochastic OptimizationTransductive Learning

Feature Dynamics as Implicit Data Augmentation: A Depth-Decomposed View on Deep Neural Network Generalization

2025-09-24 · Tianyu Ruan, Kuo Gai, Shihua Zhang arxiv

Why do deep networks generalize well? In contrast to classical generalization theory, we approach this fundamental question by examining not only inputs and outputs, but the evolution of internal features. Our study sugg…

Data Augmentation

Deep Active Learning with Augmentation-based Consistency Estimation

2020-11-05 · SeulGi Hong, Heonjin Ha, Junmo Kim, Min-Kook Choi

In active learning, the focus is mainly on the selection strategy of unlabeled data for enhancing the generalization capability of the next learning cycle. For this, various uncertainty measurement methods have been prop…

Active LearningData Augmentationimage-classificationImage Classification+1

Bootstrap Generalization Ability from Loss Landscape Perspective

2022-09-18 · Huanran Chen, Shitong Shao, Ziyi Wang, Zirui Shang 외

Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i.e., out-of-distribution data, which has different distribution from the training dataset. To address domain generalizatio…

Domain Generalization