Sparse Solutions for Single Class SVMs: A Bi-Criterion Approach

Description

In this paper we propose an innovative learning algorithm - a variation of One-class  Support Vector Machines (SVMs) learning algorithm to produce sparser solutions with much reduced computational complexities. The proposed technique returns an approximate solution, nearly as good as the solution set obtained by the classical approach, by minimizing the original risk function along with a regularization term. We introduce a bi-criterion optimization that helps guide the search towards the optimal set in much reduced time. The outcome of the proposed learning technique was compared with the benchmark one-class Support Vector machines algorithm which more often leads to solutions with redundant support vectors. Through out the analysis, the problem size for both optimization routines was kept consistent. We have tested the proposed algorithm on a variety of data sources under different conditions to demonstrate the effectiveness. In all cases the proposed algorithm closely preserves the accuracy of standard one-class  SVMs while reducing both training time and test time by several factors.

Resources

Name Format Description Link
33 daoz11.pdf https://c3.nasa.gov/dashlink/static/media/publication/daoz11.pdf
21 TROPICS Mission Page https://tropics.ll.mit.edu/CMS/tropics/Mission-Overview
21 Search results for publications that cite this dataset by its DOI. https://scholar.google.com/scholar?q=10.5067%2FBQE6IFU6Q5SK
34 TROPICS_Mission.png https://docserver.gesdisc.eosdis.nasa.gov/public/project/TROPICS/images/TROPICS_Mission.png
21 Access the dataset landing page from the GES DISC website. https://disc.gsfc.nasa.gov/datacollection/TROPICS01DMINL2B_1.0.html
21 Access the data via HTTPS https://disc2.gesdisc.eosdis.nasa.gov/data/TROPICS_L2B/TROPICS01DMINL2B.1.0/
21 Access the data via the OPeNDAP protocol. https://disc2.gesdisc.eosdis.nasa.gov/opendap/TROPICS_L2B/TROPICS01DMINL2B.1.0/contents.html
21 Use the Earthdata Search to find and retrieve data sets across multiple data centers. https://search.earthdata.nasa.gov/search?q=TROPICS01DMINL2B_1.0
33 TROPICS User Guide https://docserver.gesdisc.eosdis.nasa.gov/public/project/TROPICS/TROPICS_UserGuide_base_Sept2023.pdf
33 TROPICS01 L2B README https://docserver.gesdisc.eosdis.nasa.gov/public/project/TROPICS/TROPICS_D-MINT-183_Release_Notes_Mar2025.pdf
21 TROPICS L2B DMINT-183 ATBD https://weather.ndc.nasa.gov/tropics/quarterly/CY2024_Q4/Griffin_etal.pptx
33 daoz11.pdf https://c3.nasa.gov/dashlink/static/media/publication/daoz11.pdf

Tags

  • dashlink
  • nasa
  • ames

Topics

Categories