@InProceedings{Antoniuk-Franc-Hlavac-ACML-2014,
  IS = { zkontrolovano 26 Jun 2015 },
  UPDATE  = { 2015-04-14 },
  author = {Antoniuk, Kostiantyn and Franc, Vojt{\v e}ch and Hlav{\'a}{\v c}, V{\'a}clav},
  authorship =  {45-45-10},
  affiliation = {13133-13133-13133},
  language =    {English},
  title =       {Interval Insensitive Loss for Ordinal Classification },
  year =        {2014},
  book_pages =       {390},
  booktitle =   {JMLR Workshop and Conference Proceedings},
  editor =      {Dinh Phung, Hang Li },
 publisher = { 	Microtome Publishing},
  address =     {Brookline ,US },
  isbn =        {},
issn = {1532-4435 },
  volume =      { 39 },
  series =      { Proceedings of the Sixth Asian Conference on Machine Learning },
  pages =  { 189-204 },
  month =       {November},
  day =         {26-28 },
  venue =       {Nha Trang City, Vietnam },
  annote =      { We address a problem of learning ordinal classifier
                  from partially annotated examples. We introduce an
                  interval-insensitive loss function to measure
                  discrepancy between predictions of an ordinal
                  classifier and a partial annotation provided in the
                  form of intervals of admissible labels. The proposed
                  interval-insensitive loss is an instance of loss
                  functions previously used for learning of different
                  classification models from partially annotated
                  examples. We propose several convex surrogates of
                  the interval-insensitive loss which can be
                  efficiently optimized by existing
                  solvers. Experiments on standard benchmarks and a
                  real-life application show that ordinal classifiers
                  learned from partially annotated examples can
                  achieve accuracy close to the accuracy of
                  classifiers learned from completely annotated
                  examples.  },
  keywords =    {ordinal classification, partially annotated examples, risk minimization },
  prestige =    { international},
  project =     {TACR TE01020197, ERC-CZ LL1303,  FP7-ICT-609763 TRADR},
psurl       = { [Antoniuk-Franc-Hlavac-ACML-2014, 753 KB] },
acceptance_ratio = { 25 / 80 },
}