Minimax optimal approaches to the label shift problem

A key feature of intelligence is to transfer knowledge garnered from one task to another similar but different task. However, statistical learning has by and large been confined to procedures designed to learn from one particular task (through training data) and address the same task on new (test) data. This is inadequate for a wide range of real world applications where it is important to learn a new task, using the knowledge of a partially similar task which has already been learned. The field of transfer learning deals with these kinds of problems and has therefore attracted increasing attention in machine learning and its many varied applications. Recent applications includes computer vision [28, 10], speech recognition [14] and genre classification [5].