In supervised learning, the question of data quality and curation has been overshadowed in recent years by increasingly more powerful and expressive models that can ingest internet-scale data.

Machine Learning critically relies on the assumption that the training data is representative of the unseen instances a learner faces at test time.

This work proposes a middle ground in the form of a scalable information-theoretic generalization of CCA, termed max-sliced mutual information (mSMI).

It is crucial to quantify the uncertainty of these dynamics models when using them for planning.

Team-Nash equilibrium (TNE) predicts the outcomes of such coordinated interactions.

However, many use cases of neural network verification require solving the inverse problem, or over-approximating the set of inputs that lead to certain outputs.

Evaluating machine learning models requires evaluation data.