Bandit convex optimization is a special case of online convex optimization with partial information. In this setting, a player attempts to minimize a sequence of adversarially gen...
Abstract--Tao et al. have recently proposed the posterior probability support vector machine (PPSVM) which uses soft labels derived from estimated posterior probabilities to be mor...
I describe a framework for interpreting Support Vector Machines (SVMs) as maximum a posteriori (MAP) solutions to inference problems with Gaussian Process priors. This probabilisti...