.png){kind=icon}
返回
Model selection and error estimation without the agonizing pain
.png){kind=icon}
PRE
AI
DOI：10.1002/widm.1252.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
How can we select the best performing data-driven model? How can we rigorously estimate its generalization error? Statistical learning theory (SLT) answers these questions by deriving nonasymptotic bounds on the generalization error of a model or, in other words, by delivering upper bounding of the true error of the learned model based just on quantities computed on the available data. However, for a long time, SLT has been considered only as an abstract theoretical framework, useful for inspiring new learning approaches, but with limited applicability to practical problems. The purpose of this review is to give an intelligible overview of the problems of model selection (MS) and error estimation (EE), by focusing on the ideas behind the different SLT-based approaches and simplifying most of the technical aspects with the purpose of making them more accessible and usable in practice. We start by presenting the seminal works of the 80s until the most recent results, then discuss open problems and finally outline future directions of this field of research. This article is categorized under: Technologies > Statistical Fundamentals Algorithmic Development > Statistics
Keyword:
algorithmic stability
bootstrap
compression bound
cross validation
differential privacy
error estimation
in-sample methods
model selection
out-of-sample methods
PAC-Bayes
Rademacher complexity theory
union bound
Vapnik-Chervonenkis theory
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
11.7
论文数:
546
被引数:
5.3K
机构
引用论文
分享收藏
Purity of Spiking Agent Affects Partitioning of Prions in Plasma Protein Purification.png)
Biologicals
BiologicalsIF0
PREAI
分享收藏分享收藏分享收藏
查看更多内容