We provide a functional encryption system that supports functionality for regular languages. In our system a secret key is associated with a Deterministic Finite Automata (DFA) M....
Abstract. We propose a new graph-based label propagation algorithm for transductive learning. Each example is associated with a vertex in an undirected graph and a weighted edge be...
This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
L1 (also referred to as the 1-norm or Lasso) penalty based formulations have been shown to be effective in problem domains when noisy features are present. However, the L1 penalty...
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...