Abstract
Convergence properties of empirical risk minimizers can be conveniently expressed in terms of the associated population risk. To derive bounds for the performance of the estimator under covariate shift, however, pointwise convergence rates are required. Under weak assumptions on the design distribution, it is shown that least squares estimators (LSE) over 1-Lipschitz functions are also minimax rate optimal with respect to a weighted uniform norm, where the weighting accounts in a natural way for the non-uniformity of the design distribution. This implies that although least squares is a global criterion, the LSE adapts locally to the size of the design density. We develop a new indirect proof technique that establishes the local convergence behavior based on a carefully chosen local perturbation of the LSE. The obtained local rates are then applied to analyze the LSE for transfer learning under covariate shift.
Funding Statement
The research has been supported by the NWO/STAR grant 613.009.034b and the NWO Vidi grant VI.Vidi.192.021.
Acknowledgements
The authors would like to thank the editor, the AE and three anonymous referees for helpful comments and suggestions.
Citation
Johannes Schmidt-Hieber. Petr Zamolodtchikov. "Local convergence rates of the nonparametric least squares estimator with applications to transfer learning." Bernoulli 30 (3) 1845 - 1877, August 2024. https://doi.org/10.3150/23-BEJ1655
Information