We derive representations of higher order dual measures of risk in Lp spaces as suprema of integrals of Average Values at Risk with respect to probability measures on (0, 1] (Kusu...
Darinka Dentcheva, Spiridon Penev, Andrzej Ruszczy...
Log-linear parsing models are often trained by optimizing likelihood, but we would prefer to optimise for a task-specific metric like Fmeasure. Softmax-margin is a convex objecti...
Abstract. We deal with duality for almost convex finite dimensional optimization problems by means of the classical perturbation approach. To this aim some standard results from th...
We consider two new formulations for classification problems in the spirit of support vector machines based on robust optimization. Our formulations are designed to build in prote...
We introduce a new online convex optimization algorithm that adaptively chooses its regularization function based on the loss functions observed so far. This is in contrast to pre...