Abstract. We propose a method of unsupervised learning from stationary, vector-valued processes. A low-dimensional subspace is selected on the basis of a criterion which rewards da...
A method is introduced to learn and represent similarity with linear operators in kernel induced Hilbert spaces. Transferring error bounds for vector valued large-margin classifie...
The multi-layer bit-wise unequal error protection problem is considered for variable length block codes with feedback. Inner and outer bounds are derived for achievable performanc...
Siva K. Gorantla, Baris Nakiboglu, Todd P. Coleman...
We prove that tree isomorphism is not expressible in the language (FO + TC + COUNT). This is surprising since in the presence of ordering the language captures NL, whereas tree is...
We consider the problem of inferring the most likely social network given connectivity constraints imposed by observations of outbreaks within the network. Given a set of vertices ...