DeepAI AI Chat
Log In Sign Up

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

by   Tobias Sutter, et al.

Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribution. We employ the principle of minimum discriminating information to embed the available prior knowledge, and use distributionally robust optimization to account for uncertainty due to the limited samples. By leveraging large deviation results, we obtain explicit generalization bounds with respect to the unknown shifted distribution. Lastly, we demonstrate the versatility of our framework by demonstrating it on two rather distinct applications: (1) training classifiers on systematically biased data and (2) off-policy evaluation in Markov Decision Processes.


page 1

page 2

page 3

page 4


Robust Meta Learning for Image based tasks

A machine learning model that generalizes well should obtain low errors ...

Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes

Information-theoretic principles for learning and acting have been propo...

Memory Classifiers: Two-stage Classification for Robustness in Machine Learning

The performance of machine learning models can significantly degrade und...

Revisiting Distributionally Robust Supervised Learning in Classification

Distributionally Robust Supervised Learning (DRSL) is necessary for buil...

Unknown Examples & Machine Learning Model Generalization

Over the past decades, researchers and ML practitioners have come up wit...

Robust Federated Learning: The Case of Affine Distribution Shifts

Federated learning is a distributed paradigm that aims at training model...

Learning Diverse Representations for Fast Adaptation to Distribution Shift

The i.i.d. assumption is a useful idealization that underpins many succe...