@inproceedings{daume12distributed,
  title = {Protocols for Learning Classifiers on Distributed Data},
  author = {Hal {Daum\'e III} and Jeff Phillips and Avishek Saha and Suresh Venkatasubramanian},
  booktitle =    {Proceedings of the International Conference on Artificial Intelligence and Statistics (AIStats)},
  year =         {2012},
  address =      {Canary Islands},
  abstract =     {
    We consider the problem of learning classifiers
    for labeled data distributed across several nodes.
    The goal is to find a single classifier across all
    datasets with small approximation error, where
    the quantity to be minimized is communication
    between nodes. This setting models real-world
    communication bottlenecks in the processing of
    massive distributed datasets. We present several
    very general sampling-based solutions as well as
    some two-way protocols which have a provable
    exponential speed-up over any one-way protocol.
    We focus on core problems for noiseless
    data distributed across two or more nodes. The
    techniques we introduce are reminiscent of active
    learning, but rather than actively probing
    labels, nodes actively communicate with each
    other, each node simultaneously learning the important
    data from the other node.
  },
  keywords = {ml},
  url = {http://pub.hal3.name/#daume12distributed}
}