Matthäus Kleindessner

I am a Senior Applied Scientist at Amazon AWS in Tübingen. Before, I was a postdoc at the University of Washington and at Rutgers University. I got my PhD from the University of Tübingen in the Theory of Machine Learning Group (headed by Ulrike von Luxburg) in 2017.

Contact information:
matkle[at]amazon.com

Publications:

Evaluating the fairness of discriminative foundation models in computer vision? Conf. on Artificial Intelligence, Ethics, and Society (AIES), 2023. pdf
with J. Ali, F. Wenzel, K. Budhathoki, V. Cevher, C. Russell
When do minimax-fair learning and empirical risk minimization coincide? International Conference on Machine Learning (ICML), 2023. pdf
with H. Singh, V. Cevher, R. Chunara, and C. Russell
Unsupervised semantic segmentation with self-supervised object-centric representations. International Conference on Learning Representations (ICLR), 2023. pdf
with A. Zadaianchuk, Y. Zhu, F. Locatello, and T. Brox
Efficient fair PCA for fair representation learning. International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. pdf, poster, code
with M. Donini, C. Russell, and M. B. Zafar
Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks. Neural Information Processing Systems (NeurIPS), 2022. pdf
with M. Lohaus, K. Kenthapadi, F. Locatello, and C. Russell
Active sampling for min-max fairness. International Conference on Machine Learning (ICML), 2022. pdf, code
with J. Abernethy, P. Awasthi, J. Morgenstern, C. Russell, and J. Zhang
Individual preference stability for clustering. International Conference on Machine Learning (ICML), 2022. pdf, preliminary version, code
with S. Ahmadi, P. Awasthi, S. Khuller, J. Morgenstern, P. Sukprasert, and A. Vakilian
Score matching enables causal discovery of nonlinear additive noise models. International Conference on Machine Learning (ICML), 2022. pdf
with P. Rolland, V. Cevher, C. Russell, D. Janzing, B. Schölkopf, and F. Locatello
Measuring fairness of rankings under noisy sensitive information. Conf. on Fairness, Accountability, and Transparency (ACM FAccT), 2022. pdf
with A. Ghazimatin, C. Russell, Z. Abedjan, and J. Golebiowski
Leveling down in computer vision: Pareto inefficiencies in fair deep classifiers. Conference on Computer Vision and Pattern Recognition (CVPR), 2022. pdf
with D. Zietlow, M. Lohaus, G. Balakrishnan, F. Locatello, B. Schölkopf, and C. Russell
Pairwise fairness for ordinal regression. International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. pdf, poster, code
with S. Samadi, M. B. Zafar, K. Kenthapadi, and C. Russell
Backward-compatible prediction updates: a probabilistic approach. Neural Information Processing Systems (NeurIPS), 2021. pdf
with F. Träuble, J. von Kügelgen, F. Locatello, B. Schölkopf, and P. Gehler
Benchmarking of data-driven causality discovery approaches in the interactions of Arctic sea ice and atmosphere. Frontiers in Big Data 4, 2021. pdf
with Y. Huang, A. Munishkin, D. Varshney, P. Guo, and J. Wang
Evaluating fairness of machine learning models under uncertain and incomplete information. Conf. on Fairness, Accountability, and Transparency (ACM FAccT), 2021. pdf
with P. Awasthi, A. Beutel, J. Morgenstern, and X. Wang
Equalized odds postprocessing under imperfect group information. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020. pdf, code
with P. Awasthi and J. Morgenstern
Guarantees for spectral clustering with fairness constraints. International Conference on Machine Learning (ICML), 2019. pdf, poster, code
with S. Samadi, P. Awasthi, and J. Morgenstern
Fair k-center clustering for data summarization. International Conference on Machine Learning (ICML), 2019. pdf, poster, code
with P. Awasthi and J. Morgenstern
Crowdsourcing with arbitrary adversaries. International Conference on Machine Learning (ICML), 2018. pdf, poster, typo
with P. Awasthi
Kernel functions based on triplet comparisons. Neural Information Processing Systems (NIPS), 2017. pdf, poster
with U. von Luxburg
Lens depth function and k-relative neighborhood graph: versatile tools for ordinal data analysis. Journal of Machine Learning Research 18(58):1-52, 2017. pdf, data, large version of the embedding of the car data set
with U. von Luxburg
Dimensionality estimation without distances. International Conference on Artificial Intelligence and Statistics (AISTATS), 2015. pdf, poster
with U. von Luxburg
Uniqueness of ordinal embedding. Conference on Learning Theory (COLT), 2014. Runner-up for the best student paper award. pdf
with U. von Luxburg

All papers can also be found via Google Scholar.

PhD Thesis:

M. Kleindessner. Machine learning in a setting of ordinal distance information. University of Tübingen, 2017. pdf

Teaching: CS513 (at Rutgers --- Spring 2018)