Improving classification performance through selective instance completion

DOI10.1007/S10994-015-5500-5MaRDI QIDQ747264zbMATH OpenOpenAlexFDO

Authors Amit Dhurandhar, Karthik Sankaranarayanan

Publication date 23 October 2015

Published in Machine Learning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10994-015-5500-5

zbMATH Keywords

missing dataactive feature acquisitioninstance completion

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Towards optimal use of incomplete classification data
• Learning cost-sensitive active classifiers
• Lookahead selective sampling for incomplete data
• Classification with costly features as a sequential decision-making problem
• Classifying with confidence from incomplete information

Cites work

• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• Active learning
• Active sampling for class probability estimation and ranking
• Line search algorithms with guaranteed sufficient decrease
• Teaching Dimension and the Complexity of Active Learning
• The Generic Chaining
• The elements of statistical learning. Data mining, inference, and prediction
• Value of information lattice: exploiting probabilistic independence for effective feature subset acquisition

Cited in

(2)

• Exploratory machine learning with unknown unknowns
• Classification with costly features as a sequential decision-making problem

Describes a project that uses

Uses Software

• WEKA

This page was built for publication: Improving classification performance through selective instance completion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q747264)