We give the first tester-learner for halfspaces that succeeds universally over a wide class of
structured distributions. Our universal tester-learner runs in fully polynomial time and has the …

We consider the problem of computing the best-fitting ReLU with respect to square-loss on a
training set when the examples have been drawn according to a spherical Gaussian …

We improve the theoretical and empirical performance of neural-network (NN)-based active
learning algorithms for the non-parametric streaming setting. In particular, we introduce two …

We give the first efficient algorithm for learning halfspaces in the testable learning model
recently defined by Rubinfeld and Vasilyan (2023). In this model, a learner certifies that the …

We give a computationally-efficient PAC active learning algorithm for $ d $-dimensional
homogeneous halfspaces that can tolerate Massart noise (Massart and Nedelec, 2006) and …

We study active learning of homogeneous $ s $-sparse halfspaces in $\mathbb {R}^ d $
under the setting where the unlabeled data distribution is isotropic log-concave and each …

Active learning has become a prevalent technique for designing label-efficient algorithms,
where the central principle is to only query and fit “informative” labeled instances. It is …

We study a scenario of active learning where the input space is partitioned into different
regions and where a distinct hypothesis is learned for each region. We first introduce a new …

Recently, model stealing attacks are widely studied but most of them are focused on stealing
a single non-discrete model, eg, neural networks. For ensemble models, these attacks are …

We derive a novel active learning algorithm in the streaming setting for binary classification
tasks. The algorithm leverages weak labels to minimize the number of label requests, and …