We identify a trade-off between robustness and accuracy that serves as a guiding principle
in the design of defenses against adversarial examples. Although this problem has been …

We consider neural networks with a single hidden layer and non-decreasing positively
homogeneous activation functions like the rectified linear units. By letting the number of …

Abstract Machine learning models trained on data from the outside world can be corrupted
by data poisoning attacks that inject malicious points into the models' training sets. A …

The vast majority of theoretical results in machine learning and statistics assume that the
training data is a reliable reflection of the phenomena to be learned. Similarly, most learning …

Artificial intelligence models are becoming an integral part of modern computing systems.
Just like software inevitably has bugs, models have bugs too, leading to poor classification …

Automated AI classifiers should be able to defer the prediction to a human decision maker to
ensure more accurate predictions. In this work, we jointly train a classifier with a rejector …

Active learning is a protocol for supervised machine learning, in which a learning algorithm
sequentially requests the labels of selected data points from a large pool of unlabeled data …

We present an agnostic active learning algorithm for any hypothesis class of bounded VC
dimension under arbitrary data distributions. Most previ-ous work on active learning either …

We give a computationally efficient algorithm that learns (under distributional assumptions) a
halfspace in the difficult agnostic framework of Kearns, Schapire, and Sellie Mach. Learn …

In Bayesian persuasion, an informed sender has to design a signaling scheme that
discloses the right amount of information so as to influence the behavior of a self-interested …