Sebastian Tschiatschek

  • Postdoctoral Fellow
  • sebastian.tschiatschek@inf.ethz.ch
  • CAB F 65.1
  • +41 44 632 38 07
  • I am currently a postdoc in the Learning and Adaptive Systems Group at ETH Zurich led by Prof. Andreas Krause. Before joining ETH, I received a PhD from Graz University of Technology under supervision of Prof. Franz Pernkopf at the Signal and Speech Processing Laboratory. My research interest include submodular functions, their application in the machine learning related applications, Bayesian networks and inference under computational constraints. More information here.

Publications

2017
  • Selecting Sequences of Items via Submodular Maximization
  • , ,
  • In Conference on Artificial Intelligence (AAAI),
  • [bibtex] [abstract]
2016
2015
  • Parameter Learning of Bayesian Network Classifiers Under Computational Constraints
  • ,
  • In European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD),
  • [bibtex] [abstract]
2014
  • Introduction to Probabilistic Graphical Models
  • , ,
  • Chapter in 18, Elsevier, volume 1,
  • [bibtex] [abstract]
  • Integer Bayesian Network Classifiers
  • , ,
  • In European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD),
  • [bibtex] [abstract]
2013
  • Asymptotic Optimality of Maximum Margin Bayesian Networks
  • ,
  • In International Conference on Artificial Intelligence and Statistics (AISTATS),
  • [bibtex] [abstract]
2012
  • Bayesian Network Classifiers with Reduced Precision Parameters
  • , , ,
  • In European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD),
  • [bibtex] [abstract]
  • Convex Combinations of Maximum Margin Bayesian Network Classifiers
  • ,
  • In International Conference on Pattern Recognition Applications and Methods (ICPRAM),
  • [bibtex] [abstract]
  • Handling Missing Features in Maximum Margin Bayesian Network Classifiers
  • , ,
  • In International Workshop on Machine Learning for Signal Processing (MLSP),
  • [bibtex] [abstract]