In online classification, a learner is presented with a sequence of exam...
We give the first polynomial-time algorithm for the testable learning of...
Semi-supervised knowledge distillation is a powerful training paradigm f...
Distillation with unlabeled examples is a popular and powerful method fo...
We study the fundamental problem of learning a single neuron, i.e., a
fu...
For many learning problems one may not have access to fine grained label...
We study the problem of PAC learning halfspaces on ℝ^d with
Massart nois...
We show a statistical version of Taylor's theorem and apply this result ...
We study the problem of agnostically learning halfspaces under the Gauss...
We provide theoretical convergence guarantees on training Generative
Adv...
We study the problem of PAC learning homogeneous halfspaces in the prese...
We study the problem of PAC learning one-hidden-layer ReLU networks with...
We study the problem of agnostically learning homogeneous halfspaces in ...
We study the efficient PAC learnability of halfspaces in the presence of...
We study the problem of learning halfspaces with Massart noise in the
di...
We study the problem of estimating the parameters of a Gaussian distribu...