Recently, new polynomial approximation formulas were proposed for the reconstruction of compactly supported piecewise smooth functions from Fourier data. Formulas for zero and firs...
We show that the log-likelihood of several probabilistic graphical models is Lipschitz continuous with respect to the p-norm of the parameters. We discuss several implications ...
We present a general framework for the task of extracting specific information “on demand” from a large corpus such as the Web under resource-constraints. Given a database wit...
We present an improvement of Noviko 's perceptron convergence theorem. Reinterpreting this mistakebound as a margindependent sparsity guarantee allows us to give a PAC{style ...
Thore Graepel, Ralf Herbrich, Robert C. Williamson
Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...