Probability bounds for active learning in the regression problem

DOI10.1007/978-3-319-96941-1_14MaRDI QIDQ2417446zbMATH OpenOpenAlexFDO

Authors Carenne Ludeña, Ana K. Fermín

Publication date 12 June 2019

Full work available at URL https://arxiv.org/abs/1212.4457

zbMATH Keywords

classification problemregression problem

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02)

Abstract: In this article we consider the problem of choosing an optimal sampling scheme for the regression problem simultaneously with that of model selection. We consider a batch type approach and an on-line approach following algorithms recently developed for the classification problem. Our main tools are concentration-type inequalities which allow us to bound the supremum of the deviations of the sampling scheme corrected by an appropriate weight function.

Recommendations

• Plug-in approach to active learning
• Concentration estimates for learning with unbounded sampling
• Rademacher complexities and bounding the excess risk in active learning
• Bayesian active learning using arbitrary binary valued queries
• Rates of convergence in active learning

Cited in

(9)

• Minimax Bounds for Active Learning
• Rademacher complexities and bounding the excess risk in active learning
• Plug-in approach to active learning
• scientific article; zbMATH DE number 5957325 (Why is no real title available?)
• Upper-Confidence-Bound Algorithms for Active Learning in Multi-armed Bandits
• Rates of convergence in active learning
• Improving importance estimation in pool-based batch active learning for approximate linear regression
• The true sample complexity of active learning
• Minimax robust active learning for approximately specified regression models

This page was built for publication: Probability bounds for active learning in the regression problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2417446)