Cluster of Excellence “Machine Learning”
In general, I am interested in finding guarantees for and limitations of machine learning algorithms, as well as suitable inductive biases in the climate science context.
In our recent paper, we explored empirical distortions in climate networks originating in limited amounts of noisy data. We also found that common resampling procedures to quantify significant behaviour in climate networks do not adequately capture intrinsic network variance. It remains a matter of ongoing work to find suitable statistical corrections as well as resampling procedures that adequately capture intrinsic network variance.
- High-dimensional Probability
- Calibrated Uncertainty Quantification
- Representation Learning
- Climate Data Analysis
I studied Mathematics at the University of Heidelberg with a focus on Mathematical Statistics and Machine Learning. In my master thesis I analyized the convergence rates of Wasserstein GANs with ReLU networks. In May 2021, I started my PhD under joint supervision of Ulrike von Luxburg in the Theory of Machine Learning group (TML) at Tuebingen university, computer science department, and Bedartha Goswami from the MLCS group. I am a scholar in the International Max Planck Research School for Intelligent Systems (IMPRS-IS), a graduate school for PhD students from both university and Max-Planck-Institute in Tuebingen and Stuttgart.