Boolean functions are perhaps the most basic objects of study in theoretical computer
science. They also arise in other areas of mathematics, including combinatorics, statistical …

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 …

We study the problem of agnostic learning under the Gaussian distribution in the Statistical
Query (SQ) model. We develop a method for finding hard families of examples for a wide …

We show that any distribution on {-1,+1\}^n that is k-wise independent fools any halfspace
(or linear threshold function) h:{-1,+1\}^n→{-1,+1\}, ie, any function of the form …

There are many important high dimensional function classes that have fast agnostic learning
algorithms when strong assumptions on the distribution of examples can be made, such as …

We study the efficient learnability of geometric concept classes—specifically, low-degree
polynomial threshold functions (PTFs) and intersections of halfspaces—when a fraction of …

We study the natural question of constructing pseudorandom generators (PRGs) for low-
degree polynomial threshold functions (PTFs). We give a PRG with seed-length log n/εO (d) …

In this work we design a general method for proving moment inequalities for polynomials of
independent random variables. Our method works for a wide range of random variables …

One motivation for property testing of boolean functions is the idea that testing can provide a
fast preprocessing step before learning. However, in most machine learning applications, it …

We study the fundamental problem of transfer learning where a learning algorithm collects
data from some source distribution $ P $ but needs to perform well with respect to a different …