Paper-Conference

The seminal work of Linial, Mansour, and Nisan gave a quasipolynomial-time algorithm for learning constant-depth circuits (𝖠𝖢0) with …

Inspired by recent work on learning with distribution shift, we give a general outlier removal algorithm called iterative polynomial …

We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning …

We pose a fundamental question in computational learning theory: can we efficiently test whether a training set satisfies the …

We study the problem of PAC learning $\gamma$-margin halfspaces with Massart noise. We propose a simple proper learning algorithm, the …

We study the problem of learning under arbitrary distribution shift, where the learner is trained on a labeled set from one …

A fundamental notion of distance between train and test distributions from the field of domain adaptation is discrepancy distance. …

In the well-studied agnostic model of learning, the goal of a learner– given examples from an arbitrary joint distribution on …

Recent work of Klivans, Stavropoulos, and Vasilyan initiated the study of testable learning with distribution shift (TDS learning), …

We revisit the fundamental problem of learning with distribution shift, in which a learner is given labeled samples from training …