Using a similar reasoning as in the proof of Proposition 3.2, we can now substitute the linear

Wasserstein distance and centered around nominal (Gaussian) distributions. We show that, even under distributional ambiguity, the optimal control policy remains linear in the system's observations.

Using a similar reasoning as in the proof of Proposition 3.2, we can now substitute the linear

We propose a method for support vector machine classification using indefinite kernels. Instead of directly minimizing or stabilizing a nonconvex loss function, our algorithm simultaneously computes support vectors and a proxy kernel matrix used in forming the loss. This can be interpreted as a penalized kernel learning problem where indefinite kernel matrices are treated as a noisy observations of a true Mercer kernel. Our formulation keeps the problem convex and relatively large problems can be solved efficiently using the projected gradient or analytic center cutting plane methods. We compare the performance of our technique with other methods on several classic data sets.