I'm Marten Lienen and I care about solving problems and improving efficiency with software and machine learning. Aesthetically pleasing code makes me extra happy. At the moment, I am a PhD student at TUM's DAML group working on spatiotemporal data modeling and ML+Science in general. Before that, I worked at BMW's autonomous driving campus on 3D object detection.
For quite some time, I have also been interested in the various paradigms of thinking about programming that different programming languages have to offer and I like to read obscure books about them. You can find some of my own code on my github profile.
- Gaussian Processes are Bayesian Linear Regression
- Research Advice for Myself
- Uniform Edge Sampling from Complete k-Partite Graphs
torchode: A Parallel ODE Solver for PyTorchThe Symbiosis of Deep Learning and Differential Equations Workshop, NeurIPS, 2022
Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element NetworksInternational Conference on Learning Representations (Spotlight), 2022
Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and MoreInternational Conference on Machine Learning, 2021
FLGR: Fixed Length Gists Representation Learning for RNN-HMM Hybrid-based Neuromorphic Continuous Gesture RecognitionFrontiers in Neuroscience, 13 (2019)
Rate-Adaptive Link Quality Estimation for Coded Packet Networks2016 IEEE 41st Conference on Local Computer Networks (LCN)