===== Report: Predicting Learning Curves without the Ground Truth Hypothesis =====

//Abstract//: Upper bounds for the deviation between test error and training error of a
learning machine are derived in the case where no probability distribution
that generates the examples is assumed to exist.  The bounds are
data-dependent and algorithm dependent.  The result justifies the concept of
data-dependent and algorithm dependent VC-dimension.

<box 99% orange>
Léon Bottou, Yann Le Cun and Vladimir Vapnik:  //Report: Predicting Learning Curves without the Ground Truth Hypothesis//, May 1999.

[[http://leon.bottou.org/publications/djvu/nogroundtruth-1999.djvu|nogroundtruth-1999.djvu]]
[[http://leon.bottou.org/publications/pdf/nogroundtruth-1999.pdf|nogroundtruth-1999.pdf]]
[[http://leon.bottou.org/publications/psgz/nogroundtruth-1999.ps.gz|nogroundtruth-1999.ps.gz]]
</box>

  @misc{bottou-lecun-vapnik-1999,
    author = {Bottou, L\'{e}on and {Le Cun}, Yann and Vapnik, Vladimir},
    title = {Report: Predicting Learning Curves without the Ground Truth Hypothesis},
    year = {1999},
    month = {May},
    note = {Available on http://leon.bottou.org/papers"},
    url = {http://leon.bottou.org/papers/bottou-lecun-vapnik-1999},
  }


==== Notes ====

This is a slightly modernized rewrite of [[bottou-cortes-vapnik-94|(Bottou et al., 1994)]]
with a stronger focus on the lack of independence assumptions,
but these bounds were already present in the 1994 paper.
Please refer to the [[bottou-cortes-vapnik-94|notes associated with this earlier text]].