Fitting a graph to vector data
Name
Kelner_Fitting A.pdf
Size
211.2 KB
Format
Adobe PDF
Checksum (MD5)
cd546875a544a7001275aa490933ea92
Author(s)
Daitch, Samuel I.
Kelner, Jonathan Adam
Date Issued
January 2009
Journal
Proceedings of the 26th Annual International Conference on Machine Learning
Publisher
Association for Computing Machinery
Citation
Samuel I. Daitch, Jonathan A. Kelner, and Daniel A. Spielman. 2009. Fitting a graph to vector data. In Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09). ACM, New York, NY, USA, 201-208. DOI=10.1145/1553374.1553400 http://doi.acm.org/10.1145/1553374.1553400
Version
Author's final manuscript
Abstract
We introduce a measure of how well a combinatorial
graph ts a collection of vectors.
The optimal graphs under this measure may
be computed by solving convex quadratic
programs and have many interesting properties.
For vectors in d dimensional space, the
graphs always have average degree at most
2(d+1), and for vectors in 2 dimensions they
are always planar. We compute these graphs
for many standard data sets and show that
they can be used to obtain good solutions to
classifi cation, regression and clustering problems.
MIT Department
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Attribution-Noncommercial-Share Alike 3.0 Unported
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/1553374.1553400
