搜索结果: 1-6 共查到“管理学 PAC-Bayesian”相关记录6条 . 查询时间(0.068 秒)
PAC-Bayesian Estimation and Prediction in Sparse Additive Models
Additive models sparsity regression estimation PAC-Bayesian bounds oracle inequality MCMC stochastic search.
2012/9/17
The present paper is about estimation and prediction in high-dimensional additive models under a sparsity assumption (p nparadigm).A PAC-Bayesian strategy is investigated, delivering oracle inequaliti...
PAC-Bayesian Majority Vote for Late Classifier Fusion
Machine Learning Multimedia fusion Multi-modality search Ranking and re-ranking
2012/9/18
A lot of attention has been devoted to multimedia indexing over the past few years. In the literature, we often consider two kinds of fusion schemes: Theearly fusionand thelate fusion. In this paper w...
PAC-Bayesian Analysis of the Exploration-Exploitation Trade-off
coherent framework PAC-Bayesian Analysis Exploration-Exploitation Trade-off
2011/6/21
We develop a coherent framework for integrative
simultaneous analysis of the explorationexploitation
and model order selection tradeoffs.
We improve over our preceding results
on the same subject ...
PAC-Bayesian Analysis of Martingales and Multiarmed Bandits
PAC-Bayesian Analysis Martingales Multiarmed Bandits
2011/6/21
We present two alternative ways to apply PAC-Bayesian analysis to sequences of dependent
random variables. The first is based on a new lemma that enables to bound expectations
of convex functions of...
Robust linear regression through PAC-Bayesian truncation
Linear regression Generalization error Shrinkage
2010/10/14
We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression under $L^\infty$ constraints on the linear combination. When the input dis...
Risk bounds in linear regression through PAC-Bayesian truncation
Linear regression Generalization error Shrinkage PAC-Bayesian theorems Risk bounds Robust statistics Resistant estimators
2010/3/18
We consider the problem of predicting as well as the best linear combination
of d given functions in least squares regression, and variants of this problem including
constraints on the parameters of...