Learning Under Heavy-Tailed Covariate Shift: Rényi-Moment Guarantees, Sharp Rates, and Near-Minimax Optimality

This publication has 11 references indexed in Scilit:

• Optimally tackling covariate shift in RKHS-based nonparametric regression
  The Annals of Statistics, 2023
• Sub-Gaussian estimators of the mean of a random vector
  The Annals of Statistics, 2019
• A Vector-Contraction Inequality for Rademacher Complexities
  2016
• Rényi Divergence and Kullback-Leibler Divergence
  IEEE Transactions on Information Theory, 2014
• Concentration Inequalities
  2013
• Challenging the empirical mean and empirical variance: A deviation study
  Annales de l'Institut Henri Poincaré, Probabilités et Statistiques, 2012
• Density Ratio Estimation in Machine Learning
  2012
• Statistical analysis of kernel-based least-squares density-ratio estimation
  Machine Learning, 2011
• Concentration around the mean for maxima of empirical processes
  The Annals of Probability, 2005
• Improving predictive inference under covariate shift by weighting the log-likelihood function
  Journal of Statistical Planning and Inference, 2000