It is well-known that neural networks are computationally hard to train. On the other hand, in
practice, modern day neural networks are trained efficiently using SGD and a variety of tricks …

We describe a general technique that yields the first Statistical Query lower bounds for a
range of fundamental high-dimensional learning problems involving Gaussian distributions …

We prove bounds on the population risk of the maximum margin algorithm for two-class
linear classification. For linearly separable training data, the maximum margin algorithm has …

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 a framework for margin based active learning of linear separators. We
instantiate it for a few important cases, some of which have been previously considered in …

We give the first polynomial-time algorithm for performing linear or polynomial regression
resilient to adversarial corruptions in both examples and labels. Given a sufficiently large …

We study the task of agnostically learning halfspaces under the Gaussian distribution.
Specifically, given labeled examples $(\\mathbf {x}, y) $ from an unknown distribution on …

We introduce a new approach for designing computationally efficient learning algorithms
that are tolerant to noise, and we demonstrate its effectiveness by designing algorithms with …

We study the fundamental problems of agnostically learning halfspaces and ReLUs under
Gaussian marginals. In the former problem, given labeled examples $(\bx, y) $ from an …

We consider the problem of explaining the predictions of an arbitrary blackbox model $ f $:
given query access to $ f $ and an instance $ x $, output a small set of $ x $'s features that in …