Abstract. We investigate the generalization behavior of sequential prediction (online) algorithms, when data are generated from a probability distribution. Using some newly develop...
Density modeling is notoriously difficult for high dimensional data. One approach to the problem is to search for a lower dimensional manifold which captures the main characteristi...
We present a novel sequential clustering algorithm which is motivated by the Information Bottleneck (IB) method. In contrast to the agglomerative IB algorithm, the new sequential ...
Conventional computation models restrict to particular data structures to represent states of a computation, e.g. natural numbers, s, stacks, etc. Gurevich's Abstract State Ma...
Abstract--This paper presents a framework for privacypreserving Gaussian Mixture Model computations. Specifically, we consider a scenario where a central service wants to learn the...