Material Detail

Transductive Rademacher complexities for learning over a graph

Transductive Rademacher complexities for learning over a graph

This video was recorded at 6th Slovenian International Conference on Graph Theory, Bled 2007. Recent investigations indicate the use of a probabilistic "learning" perspective of tasks defined on a single graph, as opposed to the traditional algorithmical "computational" point of view. This note discusses the use of Rademacher complexities in this setting, and illustrates the use of Kruskal's algorithm for transductive inference based on a nearest neighbor rule.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Browse...

Disciplines with similar materials as Transductive Rademacher complexities for learning over a graph

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.