Simon Dirmeier

Simon Dirmeier

Senior Data Scientist
Academia
(Alumni)

Simon joined the SDSC as a senior data scientist in April 2022. He conducted his doctoral studies on statistical modeling of genetic data at ETH Zürich and obtained his MSc and BSc degrees at Technical University Munich in computer science. Before joining the SDSC, Simon worked as a freelance statistical consultant, and as an ML scientist at an AI startup in Lugano where he built experience in various topics ranging from generative modeling over Bayesian optimization to time series forecasting. Simon's research interests and expertise lie broadly in probabilistic machine and deep learning, causal inference, generative modeling, and their application in the natural sciences. Simon is an avid open-source software contributor and particularly enthusiastic about probabilistic programming languages, such as Stan.

Projects

IRMA

In Progress
Interpretable and Robust Machine Learning for Mobility Analysis
Engineering

FLBI

In Progress
Feature Learning for Bayesian Inference

HighFEM

In Progress
High Frequency Earthquake Modelling
Energy, Climate & Environment

Publications

Dirmeier, S.; Hong, Y.; Perez-Cruz, F. "Synthetic location trajectory generation using categorical diffusion models" Preprint 2024 View publication
Dirmeier, S. "Surjectors: surjection layers for density estimationwith normalizing flows" Journal of Open Source Software 9 94 6188 2024 View publication
Hong, Y.; Xin, Y.; Dirmeier, S.; Perez-Cruz, F.; Raubal, M. "A causal intervention framework for synthesizing mobility data and evaluating predictive neural networks" Preprint 2023 View publication
Dirmeier, S.; Hong, Y.; Xin, Y.; Perez-Cruz, F. "Uncertainty quantification and out-of-distribution detection using surjective normalizing flows" Preprint 2023 View publication
Dirmeier, S.; Albert, C.; Perez-Cruz, F. "Simulation-based inference using surjective sequential neural likelihood estimation" Preprint 2023 View publication
Dirmeier, S.; Perez-Cruz, F. "Diffusion models for probabilistic programming" Preprint 2023 View publication

Mentioned in

Case Studies

Contact us

Let’s talk Data Science

Do you need our services or expertise?
Contact us for your next Data Science project!