Remove 2013 Remove KDD Remove Optimization Remove Reporting
article thumbnail

Using Empirical Bayes to approximate posteriors for large "black box" estimators

The Unofficial Google Data Science Blog

Limitations Second order calibration, like ordinary calibration, is intended to be easy and useful, not comprehensive or optimal, and it shares some of ordinary calibration’s limitations. References [1] Omkar Muralidharan, Amir Najmi "Second Order Calibration: A Simple Way To Get Approximate Posteriors" , Technical Report, Google, 2015. [2]

KDD 40