Stable Prediction with Model Misspecification and Agnostic Distribution Shift

Understand

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 underlying true model.
• Under model misspecification, agnostic distribution shift between training and test data leads to inaccuracy of parameter estimation and instability of prediction across unknown test data.