We investigate the use of certain data-dependent estimates of the complexity of a function class, called Rademacher and Gaussian complexities. In a decision theoretic setting, we ...
We propose and analyze two strategies to learn over unordered pairs with kernels, and provide a common theoretical framework to compare them. The strategies are related to methods...
We introduce a semi-supervised support vector machine (S3 VM) method. Given a training set of labeled data and a working set of unlabeled data, S3 VM constructs a support vector m...
It is challenging to test applications and functions for which the correct output for arbitrary input cannot be known in advance, e.g. some computational science or machine learni...
We define a type system, which may also be considered as a simple Hoare logic, for a fragment of an assembly language that deals with code pointers and jumps. The typing is aimed ...