Search ETDs:
Moment Optimization towards Learning Polytopes with Few Facets
Cui, Jie

2012, Master of Science, Ohio State University, Computer Science and Engineering.

Learning the intersection of halfspaces is of interest in theoretical learning theory.


In this thesis, we consider two special cases of learning polytopes, cube and simplex. We show that the rotation of an arbitrarily oriented cube can be determined by computing the minima of the moment-generating function, given uniformly distributed samples from the cube. We also provide computational experiment results to suggest that the rotation of a simplex can be determined by computing the minima or maxima of the 3rd moment function and the (2n)th moment function.

Luis Rademacher (Advisor)
Mikhail Belkin (Committee Member)

Recommended Citations

Hide/Show APA Citation

Cui, J. (2012). Moment Optimization towards Learning Polytopes with Few Facets. (Electronic Thesis or Dissertation). Retrieved from https://etd.ohiolink.edu/

Hide/Show MLA Citation

Cui, Jie. "Moment Optimization towards Learning Polytopes with Few Facets." Electronic Thesis or Dissertation. Ohio State University, 2012. OhioLINK Electronic Theses and Dissertations Center. 15 Dec 2017.

Hide/Show Chicago Citation

Cui, Jie "Moment Optimization towards Learning Polytopes with Few Facets." Electronic Thesis or Dissertation. Ohio State University, 2012. https://etd.ohiolink.edu/

Files

osu1338403274.pdf (415.83 KB) View|Download