PhD
Chair of Data Analytics and Machine Learning at TUM
Informatik 26
Department of Computer Science
Boltzmannstr. 3
85748 Garching
Biosketch
Lukas is a PhD student at TUM working on topics at the intersection of machine learning and optimization. His current research interests lie in ML for combinatorial optimization, in particular, using machine learning to speed up traditional mixed-integer programming solvers. More broadly, he is also interested in neural combinatorial optimization, how predictions and optimization can be effectively combined, as well as in applications to societal domains such as mobility and transportation. Previously, he has worked on graph neural networks, robustness verification, and more general adversarial robustness. He has published at top ML conferences including NeurIPS, ICML, and ICLR. Some of his work got featured as spotlight presentation, and won a best paper award.
relAI Research
Graph Neural Networks: Robustness and Optimization Perspectives
I am working on topics at the intersection of machine learning and optimization, and have published at the top ML conferences, including NeurIPS, ICML, and ICLR. My current research interests lie in ML for combinatorial optimization, in particular, using machine learning to speed up traditional mixed-integer programming solvers. More broadly, I’m also interested in neural combinatorial optimization, how predictions and optimization can be effectively combined, as well as in applications to societal domains such as mobility and transportation. Previously, I have worked on graph neural networks, robustness verification, and more general adversarial robustness. I’m open to industry positions and collaborations at the intersection of machine learning and optimization – feel free to contact me!