Ass.-Prof. Mag. Lukas Steinberger Bakk. BA, PhD


I am a tenure-track Assistant Professor for Statistical Machine Learning in the Department of Statistics and Operations Research at the University of Vienna. Prior to that I was a post-doctoral researcher in the group of Angelika Rohde at the University of Freiburg and a temporary Full Professor in the Department of Mathematics at the Technical University of Munich. I received my PhD in 2015 from the University of Vienna under the supervision of Hannes Leeb.

 

My main research areas are statistical inference under differential privacy, high-dimensional data analysis, predictive inference and model selection. Please see my CV for further information.

Publications

  • Steinberger, L. and Leeb, H. (2019). Prediction when fitting simple models to high-dimensional data. Annals of Statistics 47(3), 1408--1442. pdf
  • Rohde, A. and Steinberger, L. (2018). Geometrizing rates of convergence under local differential privacy constraints. Annals of Statistics, forthcoming, arXiv:1805.01422
  • Steinberger, L. and Leeb, H. (2018). On conditional moments of high-dimensional random vectors given lower-dimensional projections. Bernoulli 24(1), 565--591. pdf
  • Bachoc, F. and Preinerstorfer, D. and Steinberger, L. (2017). Uniformly valid confidence intervals post-model-selection. Annals of Statistics, forthcoming, arXiv:1611.01043
  • Steinberger, L. (2016). The relative effects of dimensionality and multiplicity of hypotheses on the F-test in linear regression. Electronic Journal of Statistics 10, 2584--2640. doi:10.1214/16-EJS1186
  • Reschenhofer, E. and Preinerstorfer, D. and Steinberger, L. (2013). Non-monotonic penalizing for the number of structural breaks. Computational Statistics 28, 2585--2598. doi:10.1007/s00180-013-0419-4

Preprints

  • Leeb, H. and Steinberger, L. (2019). Statistical inference with F-statistics when fitting simple models to high-dimensional data. arXiv:1902.04304
  • Steinberger, L. and Leeb, H. (2018). Conditional predictive inference for high-dimensional stable algorithms. arXiv:1809.01412
  • Steinberger, L. and Leeb, H. (2016). Leave-one-out prediction intervals in linear regression models with many variables. arXiv:1602.05801

Conference and Seminar invitations

  • 10th World Congress in Probab. and Stat., Seoul, August 17-21, 2020. (pending)
  • Math. Methods of Modern Statistics, CIRM, Luminy, June 15-19, 2020. (pending)
  • Meeting in Math. Stat., CIRM, Luminy, December 16-20, 2019. (pending)
  • CMStat, Session `Recent developments in privacy-preserving data analysis', London, December 14-16, 2019. (pending)
  • Statistics Seminar, DPMMS, University of Cambridge, June 7, 2019.
  • Seminar `Statistics and Risk Management', Technical University of Munich, June 5, 2019.
  • KASTEL, Karlsruhe Institute of Technology, March 1, 2019.
  • Workshop on `Mathematical Foundations of Statistical Uncertainty Quantification', Freiburg, February 18, 2019.
  • Three part guest-lecture on `Statistical estimation under differential privacy', Ruhr-University Bochum, January 14–16, 2019.
  • Meeting in Mathematical Statistics, Fréjus, December 18, 2018.
  • FDM Seminar, University of Freiburg, November 9, 2018.
  • MSRaI Workshop, Vienna, July 14, 2018.
  • MFO, Oberwolfach, Workshop on `Matrix estimation meets statistical network analysis', June 18, 2018.
  • CFE-CMStat, Session `Model Selection and Inference', London, December 17, 2017.
  • Statistics Colloquium, TU Wien, Vienna, December 6, 2017.
  • IMT, Université Paul Sabatier, Toulouse, October 18, 2016.
  • Workshop on Model Selection, KU Leuven, September 8, 2016.