Material Detail

Parallel Online Learning

Parallel Online Learning

This video was recorded at NIPS Workshops, Whistler 2009. A fundamental limit on the speed of training and prediction is imposed by bandwidth: there is a finite amount of data that a computer can access in a fixed amount of time. Somewhat surprisingly, we can build an online learning algorithm fully capable of hitting this limit. I will discuss approaches for breaking the bandwidth limit, including empirical results.... 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.