I am a PhD student at the Division of Systems and Control within the Department of Information Technology and the Centre for Interdisciplinary Mathematics in Uppsala, supervised by Fredrik Lindsten, Dave Zachariah, and Erik Sjöblom. The main focus of my PhD studies is uncertainty-aware deep learning. Currently, I am particularly interested in analyzing and evaluating calibration of probabilistic models.
For my Master's thesis in Mathematics at TU Munich, I explored a delay differential equation system of quorum sensing in Pseudomonas aeruginosa. For the numerical analysis of the investigated system I used and contributed to DelayDiffEq.jl, a delay differential equation solver in the Julia programming language.
Moreover, during my Master's studies I worked on a research project at the Institute of Computational Biology, Munich, and investigated post-translational histone modifications using hidden Markov models.
During my medical studies at LMU Munich I was part of a research group at the Center of Neuropathology, Munich, and performed sequencing and imaging analysis of 5-hmC in brain tumours.
Widmann, D., Lindsten, F., & Zachariah, D. (2019). Calibration measures in multi-class classification. Swedish Symposium on Deep Learning (SSDL), Norrköping, Sweden.
Vaicenavicius, J., Widmann, D., Andersson, C., Lindsten, F., Schön, T. B. & Roll, J. (2018). Evaluation of model calibration in classification. Machine Learning Summer School (MLSS) 2018, Madrid, Spain.
Widmann, D., & Kuttler, C. (2018). Quorum sensing of Pseudomonas putida in continuous cultures. 11th European Conference on Mathematical and Theoretical Biology (ECMTB), Lisbon, Portugal.
Vaicenavicius, J., Widmann, D., Andersson, C., Lindsten, F., Schön, T. B. & Roll, J. (2018). Calibrated predictive uncertainty in classification with neural networks. Reglermöte 2018, Stockholm, Sweden. abstract
Widmann, D., Lindsten, F., & Zachariah, D. (2021). Calibration tests beyond classification. International Conference on Learning Representations (ICLR) 2021. full-text webpage code video slides poster
Widmann, D., Lindsten, F., & Zachariah, D. (2019). Calibration tests in multi-class classification: A unifying framework. Conference on Neural Information Processing Systems (NeurIPS) 2019. full-text arXiv code video slides poster
Vaicenavicius, J., Widmann, D., Andersson, C., Lindsten, F., Roll, J. & Schön, T. B. (2019). Evaluating model calibration in classification. Proceedings of Machine Learning Research, in PMLR 89:3459-3467. full-text arXiv code
Kraus, T. F. J., Globisch, D., Wagner, M., Eigenbrod, S., Widmann, D., Münzel, M., Müller, M., Pfaffeneder, T., Hackner, B., Feiden, W., Schüller, U., Carell, T., Kretzschmar, H. A. (2012). Low values of 5-hydroxymethylcytosine (5hmc), the “sixth base,” are associated with anaplasia in human brain tumors. International Journal of Cancer, 131(7), 1577–1590. full-text