In this paper, we present a substantially generalized co-clustering framework wherein any Bregman divergence can be used in the objective function, and various conditional expectation based constraints can be considered based on the statistics that need to be preserved. Analysis of the coclustering problem leads to the minimum Bregman information principle, which generalizes the maximum entropy principle, and yields an elegant meta algorithm that is guaranteed to achieve local optimality. Our methodology yields new algorithms and also encompasses several previously known clustering and co-clustering algorithms based on alternate minimization.

Abstract: ....Cross-association is a joint decomposition of a binary matrix into disjoint row and column groups such that the rectangular intersections of groups are homogeneous. Starting from first principles, we furnish a clear, information theoretic criterion to choose a good cross-association as well as its parameters, namely, the number of row and column groups. We provide scalable algorithms to approach the optimal. Our algorithm is parameter-free, and requires no user intervention. In practice it scales linearly with the problem size, and is thus applicable to very large matrices.

Abstract: Co-clustering, or simultaneous clustering of rows and columns of a two-dimensional data matrix, is rapidly becoming a powerful data analysis technique. Co-clustering has enjoyed wide success in varied application domains such as text clustering, gene-microarray analysis, natural language processing and image, speech and video analysis. In this paper, we introduce a partitional co-clustering formulation that is driven by the search for a good matrix approximation—every co-clustering is associated with an approximation of the original data matrix and the quality of co-clustering is determined by the approximation error.

The present invention relates to a scaleable automatic method of using multiple techniques to generate models and combinations of models from data and prior knowledge. The system provides unprecedented ease of use in that many of the choices of technique and parameters are explored automatically by the system, without burdening the user, and provides scaleable learning over distributed processors to achieve speed and data-handling capacity to satisfy the most demanding requirements.

The authors propose a “heuristic greedy iterative” algorithm to estimate the probability of a keyword subset being the caption of an image. Correlations between keywords are analyzed by “Automatic Local Analysis” of text information retrieval. In addition, a new image generation probability estimation method is proposed based on region matching. The authors’ iterative annotation algorithm incorporates the keyword correlations and the region matching approaches to improve image annotation.