===== The Huller: a simple and efficient online SVM =====

We propose a novel online kernel classifier algorithm that converges to the
Hard Margin SVM solution. The same update rule is used to both add and
remove support vectors from the current classifier. Experiments suggest that
this algorithm matches the SVM accuracies after a single pass over the
training examples. This algorithm is attractive when one seeks a competitive
classifier with large datasets and limited computing resources.

<box 99% orange>
Antoine Bordes and Léon Bottou: **The Huller: a simple and efficient online SVM**,  //Machine Learning: ECML 2005//, 505-512, Lecture Notes in Artificial Intelligence, LNAI 3720, Springer Verlag, 2005.

[[http://leon.bottou.org/publications/djvu/ecml-2005.djvu|ecml-2005.djvu]]
[[http://leon.bottou.org/publications/pdf/ecml-2005.pdf|ecml-2005.pdf]]
[[http://leon.bottou.org/publications/psgz/ecml-2005.ps.gz|ecml-2005.ps.gz]]
</box>

  @inproceedings{bordes-bottou-2005,
    author = {Bordes, Antoine and Bottou, {L\'{e}on}},
    title = {The Huller: a simple and efficient online SVM},
    year = {2005},
    booktitle = {Machine Learning: ECML 2005},
    pages = {505-512},
    series = {Lecture Notes in Artificial Intelligence, LNAI~3720},
    publisher = {Springer Verlag},
    url = {http://leon.bottou.org/papers/bordes-bottou-2005},
  }

===== Links =====

  *  This underrated algorithm is the precursor of LaSVM [[bordes-ertekin-weston-bottou-2005|(Bordes & al., 2005)]].
  *  [[http://user.cs.tu-berlin.de/~nowozin/|Sebastian Nowozin]] at TU-Berlin proposes a free [[http://user.cs.tu-berlin.de/~nowozin/huller|implementation of the Huller]] in C.