work +49 6151 16-57 243
fax +49 6151 16-57 241
Dominik Linzner received his diploma in physics from the University of Kaiserslautern (Germany) in January 2016. His background is theoretical quantum optics with a focus on the numerical study of many-body systems using tensor-network based algorithms.
His research focuses on the development of novel inference algorithms for high-throughput biological data. In particular, he is interested in learning the underlying topology of data-generating processes (network inference) in the high p low n regime (less samples than sample dimension) and studying the dynamics of processes on complex networks.
He is currently interested in variational methods, rendering complex and high-dimensional problems tractable and Bayesian inference methods for the integration of prior knowledge and stabilization of high-dimensional predictions in the presence of small sample numbers.
Dominik Linzner is a PhD student at the Bioinspired Communication Systems Lab since March 2017 and is part of the PrECISE project funded the European Unions Horizon 2020 research and innovation programme. The project focuses on the creation of personalized therapies for prostate cancer patients.
Engelmann, N. and Linzner, D. and Koeppl, H. (2020):
Continuous-Time Bayesian Networks with Clocks.
International Conference on Machine Learning 2020, virtual Conference, 12.-18.07., [Conference or Workshop Item]
Linzner, D. and Heinz, K. (2020):
A Variational Perturbative Approach to Planning in Graph-based Markov Decision Processes.
AAAI-20 - Thirty-Fourth AAAI Conference on Artificial Intelligence, New York, USA, February 7-12, 2020, [Conference or Workshop Item]
Linzner, D. and Schmidt, M. and Koeppl, H. (2019):
Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data.
33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, 09.-13.12., [Conference or Workshop Item]
Linzner, D. and Koeppl, H. (2018):
Cluster Variational Approximations for Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data.
32. Conference on Neural Information Processing Systems, Montreal, Canada, December 3-8, 2018, [Conference or Workshop Item]