Material Detail

From clustering to algorithms

From clustering to algorithms

This video was recorded at Workshop on Optimization and Inference in Machine Learning and Physics, Lavin 2005. In this talk we firstly provide a rigorous probabilistic proof of the clustering phenomenon taking place in the space of solution of random combinatorial problems. Secondly we will discuss a generalization of the survey propagation equations efficiently exploring the clustered geometry. Finally, we discuss the computational consequences of the possibility of finding single clusters by describing a \"physical\" lossy compression scheme. Performance are optimized when the number of well separated clusters is maximal in the underlying physical model.

Quality

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

More about this material

Comments

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