.png){kind=icon}
返回
DEVIATION OPTIMAL LEARNING USING GREEDY Q-AGGREGATION
.png){kind=icon}
OA
AI
DOI：10.1214/12-AOS1025.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Given a finite family of functions, the goal of model selection aggregation is to construct a procedure that mimics the function from this family that is the closest to an unknown regression function. More precisely, we consider a general regression model with fixed design and measure the distance between functions by the mean squared error at the design points. While procedures based on exponential weights are known to solve the problem of model selection aggregation in expectation, they are, surprisingly, sub-optimal in deviation. We propose a new formulation called Q-aggregation that addresses this limitation; namely, its solution leads to sharp oracle inequalities that are optimal in a minimax sense. Moreover, based on the new formulation, we design greedy Q-aggregation procedures that produce sparse aggregation models achieving the optimal rate. The convergence and performance of these greedy procedures are illustrated and compared with other standard methods on simulated examples.
Keyword:
Regression
model selection
model averaging
greedy algorithm
exponential weights
oracle inequalities
deviation bounds
lower bounds
deviation suboptimality
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:
3.7
论文数:
2.8K
被引数:
2.9W
机构
引用论文
KULLBACK-LEIBLER AGGREGATION AND MISSPECIFIED GENERALIZED LINEAR MODELSKULLBACK-LEIBLER聚合和错误指定的广义线性模型.png)
ANNALS OF STATISTICSOAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏Graphene/Ionic Liquid Binary Electrode Material for High Performance Supercapacitor用于高性能超级电容器的石墨烯/离子液体二元电极材料
PREAI
分享收藏分享收藏
分享收藏分享收藏
查看更多内容