Overview
Welcome! On this web page, I give an overview over my research and background. My name is Philipp Geiger, I'm a research scientist at Bosch Center for Artificial Intelligence. Before, I did my doctorate in computer science at Max Planck Institute for Intelligent Systems, and a diplom in mathematics at Heidelberg University with philosophy as a minor subject.
Research scope: I conduct research broadly in the areas of machine learning and multiagent systems, often including theoretical guarantees, validation, statistics, dynamical systems, deep learning and interpretability of models. Currently I am focusing on deep imitation learning and data-driven realistic simulations. Previously, I also worked in the areas of causal inference and mathematical logic.
Selected publications:
- Fail-Safe Adversarial Generative Imitation Learning. (2022). TMLR.
- Learning game-theoretic models of multiagent trajectories using implicit layers. (2021). AAAI.
- Coordinating users of shared facilities via data-driven predictive assistants and game theory. (2019). UAI. [Slides.]
Transfer: I also work on the multi-stakeholder problem of co-evolving innovative research with applications that are relevant for society. In particular, I consider applications in the areas of safe automated driving and resource-efficient sharing economy.
Further links: my profiles on Google Scholar, GitHub.