@InProceedings{KPR90,
  author = 	 { Anthony Kuh and Thomas Petsche and Ronald L. Rivest },
  title = 	 { Learning time-varying concepts },
  pages = 	 { 183--189 },
  url =          { http://books.nips.cc/papers/files/nips03/0183.pdf },                  
  booktitle =    { Proceedings of the 1990 Conference on Advances in Neural Information Processing Systems 3 },
  OPTpublisher = { Morgan Kaufmann },
  editor = 	 { Richard P. Lippmann and John E. Moody and David S. Touretzky },
  date =         { 1990 },                  
  OPTyear = 	 { 1990 },
  OPTmonth = 	 { November 26--29, },
  eventtitle =   { NIPS'90 },
  eventdate =    { 1990-11-26/1990-11-29 },
  venue =        { Denver, Colorado },
  abstract =     {
        This work extends computational learning theory to situations in which concepts vary over time,
        e.g. system identification of a time-varying plant.  We have extended formal definitions of
        concepts and learning to provide a framework in which an algorithm can track a concept as it
        evolves over time.  Given this framework and focusing on memory-based algorithms, we have
        derived some PAC-style sample complexity results that determine, for example, when tracking
        is feasible.  We have also used a similar framework and focused on incremental tracking algorithms
        for which we have derived some bounds on the mistake or error rates for some specific concept
        classes.                  
                 },
}