A Unified Algorithmic Framework for Multi-Dimensional Scaling

In this paper, we propose a unified algorithmic framework for solving many known variants of MDS. Our algorithm is a simple iterative scheme with guaranteed convergence, and is modular; by changing the internals of a single subroutine in the algorithm, we can switch cost functions and target spaces easily. In addition to the formal guarantees of convergence, our algorithms are accurate; in most cases, they converge to better quality solutions than existing methods, in comparable time. We expect that this framework will be useful for a number of MDS variants that have not yet been studied. Categories and Subject Descriptors H.2.8 [Database applications]: Data mining; F.2.2 [Nonnumerical algorithms and problems]: Geometrical algorithms Keywords Multi-dimensional scaling, dimensionality reduction.

• Type: Journal
• Year: 2010
• Where: CORR
• Authors: Arvind Agarwal, Jeff M. Phillips, Suresh Venkatasubramanian
• Keywords: Algorithms, CORR 2010, Education, Simple Iterative Scheme, Unified Algorithmic Framework