Localized Upper and Lower Bounds for Some Estimation Problems
Abstract
We derive upper and lower bounds for some statistical estimation problems. The upper bounds are established for the Gibbs algorithm. The lower bounds, applicable for all statistical estimators, match the obtained upper bounds for various problems. Moreover, our framework can be regarded as a natural generalization of the standard minimax framework, in that we allow the performance of the estimator to vary for different possible underlying distributions according to a pre-defined prior.
Cite
Text
Zhang. "Localized Upper and Lower Bounds for Some Estimation Problems." Annual Conference on Computational Learning Theory, 2005. doi:10.1007/11503415_35Markdown
[Zhang. "Localized Upper and Lower Bounds for Some Estimation Problems." Annual Conference on Computational Learning Theory, 2005.](https://mlanthology.org/colt/2005/zhang2005colt-localized/) doi:10.1007/11503415_35BibTeX
@inproceedings{zhang2005colt-localized,
title = {{Localized Upper and Lower Bounds for Some Estimation Problems}},
author = {Zhang, Tong},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2005},
pages = {516-530},
doi = {10.1007/11503415_35},
url = {https://mlanthology.org/colt/2005/zhang2005colt-localized/}
}