University of Cambridge > > Statistics > Minimax Lower Bounds

Minimax Lower Bounds

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Richard Samworth.

In estimation problems, lower bounds for the minimax risk are commonly used for assessing the quality of estimators. In this talk, a collection of such minimax lower bounds will be presented that involve a general class of dissimilarity measures between probabilities known as $f$-divergences. Connections to Kolmogorov’s notion of metric entropy will also be discussed. Further, two applications to nonparametric estimation problems involving shape restrictions will be presented.

This talk is part of the Statistics series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity