Many machine learning systems rely on data collected in the wild from untrusted sources,
exposing the learning algorithms to data poisoning. Attackers can inject malicious data in …

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 …

Abstract We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-
convex optimization. The algorithm performs stochastic gradient descent, where in each step …

Instance-and Label-dependent label Noise (ILN) widely exists in real-world datasets but has
been rarely studied. In this paper, we focus on Bounded Instance-and Label-dependent …

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 problem of {\em distribution-independent} PAC learning of halfspaces in the
presence of Massart noise. Specifically, we are given a set of labeled examples $(\bx, y) …

We prove novel algorithmic guarantees for several online problems in the smoothed
analysis model. In this model, at each time step an adversary chooses an input distribution …

Fairness-aware learning involves designing algorithms that do not discriminate with respect
to some sensitive feature (eg, race or gender). Existing work on the problem operates under …

We study the problem of learning halfspaces with Massart noise in the distribution-specific
PAC model. We give the first computationally efficient algorithm for this problem with respect …

We study the\emphapproximate recovery problem: Given corrupted 1-bit measurements of
the form sign (w^*⋅ x_i), recover a vector w that is a good approximation to w^*∈\Re^ d …