.png){kind=icon}
返回
OPTIMAL LEARNING WITH Q-AGGREGATION
.png){kind=icon}
OA
AI
DOI：10.1214/13-AOS1190.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We consider a general supervised learning problem with strongly convex and Lipschitz loss and study the problem of model selection aggregation. In particular, given a finite dictionary functions (learners) together with the prior, we generalize the results obtained by Dai, Rigollet and Zhang [Ann. Statist. 40 (2012) 1878-1905] for Gaussian regression with squared loss and fixed design to this learning setup. Specifically, we prove that the Q-aggregation procedure outputs an estimator that satisfies optimal oracle inequalities both in expectation and with high probability. Our proof techniques somewhat depart from traditional proofs by making most of the standard arguments on the Laplace transform of the empirical process to be controlled.
Keyword:
Learning theory
empirical risk minimization
aggregation
empirical processes 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:
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分享收藏分享收藏分享收藏SHARP ORACLE INEQUALITIES FOR AGGREGATION OF AFFINE ESTIMATORS仿射估计量聚合的尖锐ORACLE不等式ANNALS OF STATISTICSOAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity通过指数加权、尖锐的pac-bayesian边界和稀疏性进行聚合MACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏EXPONENTIAL SCREENING AND OPTIMAL RATES OF SPARSE ESTIMATION稀疏估计的指数筛选和最佳速率ANNALS OF STATISTICSOAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏
查看更多内容