License
When quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.FSTTCS.2015.38
URN: urn:nbn:de:0030-drops-56375
URL: http://drops.dagstuhl.de/opus/volltexte/2015/5637/
Go to the corresponding LIPIcs Volume Portal


Daumé III, Hal ; Khuller, Samir ; Purohit, Manish ; Sanders, Gregory

On Correcting Inputs: Inverse Optimization for Online Structured Prediction

pdf-format:
27.pdf (0.5 MB)


Abstract

Algorithm designers typically assume that the input data is correct, and then proceed to find "optimal" or "sub-optimal" solutions using this input data. However this assumption of correct data does not always hold in practice, especially in the context of online learning systems where the objective is to learn appropriate feature weights given some training samples. Such scenarios necessitate the study of inverse optimization problems where one is given an input instance as well as a desired output and the task is to adjust the input data so that the given output is indeed optimal. Motivated by learning structured prediction models, in this paper we consider inverse optimization with a margin, i.e., we require the given output to be better than all other feasible outputs by a desired margin. We consider such inverse optimization problems for maximum weight matroid basis, matroid intersection, perfect matchings, minimum cost maximum flows, and shortest paths and derive the first known results for such problems with a non-zero margin. The effectiveness of these algorithmic approaches to online learning for structured prediction is also discussed.

BibTeX - Entry

@InProceedings{daumiii_et_al:LIPIcs:2015:5637,
  author =	{Hal Daum{\'e} III and Samir Khuller and Manish Purohit and Gregory Sanders},
  title =	{{On Correcting Inputs: Inverse Optimization for Online Structured Prediction}},
  booktitle =	{35th IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS 2015)},
  pages =	{38--51},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-939897-97-2},
  ISSN =	{1868-8969},
  year =	{2015},
  volume =	{45},
  editor =	{Prahladh Harsha and G. Ramalingam},
  publisher =	{Schloss Dagstuhl--Leibniz-Zentrum fuer Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{http://drops.dagstuhl.de/opus/volltexte/2015/5637},
  URN =		{urn:nbn:de:0030-drops-56375},
  doi =		{10.4230/LIPIcs.FSTTCS.2015.38},
  annote =	{Keywords: Inverse Optimization, Structured Prediction, Online Learning}
}

Keywords: Inverse Optimization, Structured Prediction, Online Learning
Seminar: 35th IARCS Annual Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS 2015)
Issue Date: 2015
Date of publication: 11.12.2015


DROPS-Home | Fulltext Search | Imprint Published by LZI