Stable Prediction with Model Misspecification and Agnostic Distribution Shift
national conference on artificial intelligence, 2020.
For many machine learning algorithms, two main assumptions are required to guarantee performance. One is that the test data are drawn from the same distribution as the training data, and the other is that the model is correctly specified. In real applications, however, we often have little prior knowledge on the test data and on the und...More
PPT (Upload PPT)