Computer Science – Learning
Scientific paper
2010-03-02
Computer Science
Learning
18 pages, 7 figures. This version fixes a bug in the proof of Theorem 6.1 (dimensionality reduction for spherical data). The s
Scientific paper
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 \emph{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. Our framework extends to embedding high-dimensional points lying on a sphere to points on a lower dimensional sphere, preserving geodesic distances. As a compliment to this result, we also extend the Johnson-Lindenstrauss Lemma to this spherical setting, where projecting to a random $O((1/\eps^2) \log n)$-dimensional sphere causes $\eps$-distortion.
Agarwal Arvind
Phillips Jeff M.
Venkatasubramanian Suresh
No associations
LandOfFree
A Unified Algorithmic Framework for Multi-Dimensional Scaling does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A Unified Algorithmic Framework for Multi-Dimensional Scaling, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Unified Algorithmic Framework for Multi-Dimensional Scaling will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-663665