I pursue my Ph.D. in the Data Analytics and Machine Learning (DAML) group at the Technical University of Munich (TUM), where I am supervised by Stephan Günnemann.
My research focuses on efficient machine learning methods for uncertainty estimation for different input (e.g. tabular, images, graphs, sequential data) and output types (e.g. categories, real values, positive counts). In particular, I am interested in defining desiderata, models and evaluation methods for practical uncertainty estimation in realworld applications. Other research interests include hierarchical and causal inference, robust machine learning and efficient machine learning.
If you are interested in discussing with me, contact me per email or on twitter :)


Natural Posterior Network
Deep Bayesian Uncertainty for Exponential Family Distributions  ICLR 2022

EndtoEnd Learning of Probabilistic Hierarchies on Graphs
ICLR 2022

Differentiable DAG Sampling
ICLR 2022

Graph Posterior Network
Bayesian Predictive Uncertainty for Node Classification  NeurIPS 2021

Evaluating Robustness of Predictive Uncertainty Estimation
Are Dirichletbased Models Reliable?  ICML 2021

On Outofdistribution Detection with EnergyBased Models
UDL 2021 (ICML)

Posterior Network
Uncertainty Estimation without OOD Samples via DensityBased PseudoCounts  NeurIPS 2020

Scikitnetwork
Graph Analysis in Python  JMLR 2020

Uncertainty on Asynchronous Time Event Prediction
ICLR 2022

Tree Sampling Divergence
An InformationTheoretic Metric for Hierarchical Graph Clustering  IJCAI 2019

Multiscale Clustering in Graphs using Modularity
KTH Publication Library (DiVA) 2019

Hierarchical Graph Clustering using Node Pair Sampling
MLG 2018 (KDD)