Material Detail

Distribution-Independent Reliable Learning

Distribution-Independent Reliable Learning

This video was recorded at 27th Annual Conference on Learning Theory (COLT), Barcelona 2014. We study several questions in the reliable agnostic learning framework of Kalai et al. (2009), which captures learning tasks in which one type of error is costlier than other types. A positive reliable classifier is one that makes no false positive errors. The goal in the positive reliable agnostic framework is to output a hypothesis with the following properties: (i) its false positive error rate is at most ϵ, (ii) its false negative error rate is at most ϵ more than that of the best positive reliable classifier from the class. A closely related notion is fully reliable agnostic learning, which considers partial classifiers that are allowed to predict "unknown" on some inputs. The best fully... Show More


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

More about this material


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