Christoph Lampert
[intermediate] Training with Fairness and Robustness Guarantees
Summary
In times where more and more automatic decision systems are deployed for real-world tasks, machine learning researchers have to make sure that the systems they create are not only accurate but also robust and fair in the decisions they make. The lectures will give an introduction what these terms mean scientifically and will discuss recent developments for achieving them.
Syllabus
- Introduction to classifier robustness
- How to make a classifier robust
- Introduction to algorithmic fairness
- How to make a classifier fair
- Robust fair learning from unreliable data
References
Solon Barocas, Moritz Hardt, Arvind Narayanan. “Fairness and Machine Learning: Limitations and Opportunities”, https://fairmlbook.org/
Nikola Konstantinov. “Fairness and Robustness in Machine Learning”. PhD Thesis, IST Austria (2022). https://shorturl.at/iyP16
Pre-requisites
Elementary concepts of linear algebra (vectors, matrices, norms). Elementary concepts of calculus (continuity, derivatives, integrals). Elementary concepts of probability (random variables, conditional probability, expected value). Elementary concepts of machine learning (classification, loss functions, empirical risk minimization, held-out data for evaluation).
Short bio
Christoph Lampert received the PhD degree in mathematics from the University of Bonn in 2003. Afterwards he held postdoctoral positions at the German Research Center for Artificial Intelligence and the Max-Planck Institute for Biological Cybernetics. In 2010 he joined the Institute of Science and Technology Austria (ISTA) first as an Assistant Professor and since 2015 as a Professor. There, he leads the research group for Machine Learning and Computer Vision and since 2019 he is also the director of ISTA’s ELLIS unit. His research on machine learning and computer vision has won international and national awards, including a best paper prize at CVPR 2008. In 2012 he was awarded an ERC Starting Grant (consolidator phase) by the European Research Council. In 2019 and 2021 he was a member of the ERC Starting Grant evaluation panel. He is a former Associate Editor in Chief of the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and a current member of the editorial board of the International Journal of Computer Vision (IJCV) and the Journal for Machine Learning Research (JMLR).
