The fundamental problem of non-parametric two-sample testing consists in detecting the difference between any two distributions having access only to samples from these.

Then momentum acceleration is also introduced into our dual accelerating update step.

Then momentum acceleration is also introduced into our dual accelerating update step.

Pruning methods for neural networks [LeCun et al., 1989] replace dense weight matrices by sparse

Imitation learning from human feedback studies how to train well-performed imitation agents with an annotator's relative comparison of two demonstrations

We study the implicit bias of optimization in robust empirical risk minimization (robust ERM) and its connection with robust generalization.