Talk by John Langford, Yahoo! Research
Yahoo! Academic Relations & the Columbia University Center for Computational Learning Systems Present:
Title: Towards Efficient Parallel Learning
Online learning approaches are often the most efficient methods for learning on a dataset. For really big datasets however, they are not efficient enough, simply because the bandwidth requirements are too great. How can we effectively apply and adapt our efficient online learning algorithms to parallel environments? I will describe what we've learned so far for both multicore and multinode parallelization.
John Langford is a computer scientist, working as a senior researcher at Yahoo! Research. He studied Physics and Computer Science at the California Institute of Technology, earning a double bachelor's degree in 1997, and received his Ph.D. from Carnegie Mellon University in 2002. Previously, he was affiliated with the Toyota Technological Institute and IBM's Watson Research Center. He is also the author of the popular Machine Learning weblog, hunch.net.
Talk Sponsored by CCLS and Yahoo! Academic Relations