Direct importance estimation for covariate shift adaptation

DOI10.1007/s10463-008-0197-xzbMath1294.62069MaRDI QIDQ144623

Hisashi Kashima, Masashi Sugiyama, Taiji Suzuki, Shinichi Nakajima, Paul Von Bünau, Motoaki Kawanabe, Masashi Sugiyama, Taiji Suzuki, Shinichi Nakajima, Paul von Bünau, Motoaki Kawanabe, Hisashi Kashima

Publication date: 30 August 2008

Published in: Annals of the Institute of Statistical Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10463-008-0197-x

zbMATH Keywords

importance sampling; Kullback-Leibler divergence; model misspecification; covariate shift; likelihood cross validation

Mathematics Subject Classification ID

62G08: Nonparametric regression and quantile regression

62G05: Nonparametric estimation

Related Items

Direct importance estimation for covariate shift adaptation, densratio, Statistical analysis of distance estimators with density differences and density ratios, Domain adaptation and sample bias correction theory and algorithm for regression, Statistical analysis of kernel-based least-squares density-ratio estimation, Active learning for noisy oracle via density power divergence, Semi-supervised learning of class balance under class-prior change by distribution matching, Direct density-ratio estimation with dimensionality reduction via least-squares hetero-distributional subspace search, Machine learning with squared-loss mutual information, Semi-supervised speaker identification under covariate shift, Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimation, Equal percent bias reduction and variance proportionate modifying properties with mean-covariance preserving matching, Computational complexity of kernel-based density-ratio estimation: a condition number analysis, Least-squares two-sample test, Transfer estimation of evolving class priors in data stream classification, Pool-based active learning in approximate linear regression, A theory of learning from different domains, Change-point detection in time-series data by relative density-ratio estimation, Domain Adaptation Using the Grassmann Manifold, Semi-supervised logistic discrimination via labeled data and unlabeled data from different sampling distributions, Least-Squares Independent Component Analysis

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Direct importance estimation for covariate shift adaptation
• On Kullback-Leibler loss and density estimation
• Sharper bounds for Gaussian and empirical processes
• Improving predictive inference under covariate shift by weighting the log-likelihood function
• A Bennett concentration inequality and its application to suprema of empirical processes
• Convergence rates for density estimation with Bernstein polynomials.
• Nonparametric and semiparametric models.
• Weak convergence and empirical processes. With applications to statistics
• Smoothed functional principal components analysis by choice of norm
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Local Rademacher complexities
• 10.1162/153244302760185252
• Input-dependent estimation of generalization error under covariate shift
• Asymptotic Properties of Maximum Likelihood Estimators and Likelihood Ratio Tests Under Nonstandard Conditions
• Sample Selection Bias as a Specification Error
• Improving the sample complexity using global data
• Trading Variance Reduction with Unbiasedness: The Regularized Subspace Information Criterion for Robust Model Selection in Kernel Regression
• Soft margins for AdaBoost
• New concentration inequalities in product spaces