CV

Education

• Ph.D in Machine Learning. AIML Lab, University of St. Gallen, 2019 - 2024 (expected)
  • Topic: Self-Supervised Representation Learning of Populations of Neural Networks.
  • Advisor: Prof. Dr. Borth.
  • Funding: HSG Basic Research Fund and Google Research Scholar Award (contact: Erik Vee, Google Research).
  • Research Visit: Michael Mahoney at ICSI, Berkeley, March-May 2023.
• M.Sc. in General Mechanical Enginnering, RWTH Aachen University, 2016-2018.
  • Focus on Simulation Science, Numerical Math and Optimization.
  • Thesis: “Global Deterministic Training of Artificial Neural Networks.”, Advisor: Prof. Dr. Mitsos.
• B.Sc. Mechanical Engineering. RWTH Aachen University, 2012-2016.
  • Focus on Energy Technology and Automatic Control.
  • Thesis: “Dynamic Reference Trajectory Generation for a Model Predictive Wind Turbine Controller”. Advisor: Prof. Dr. Abel.
• Erasmus Exchange, Aalto University, Helsinki, Finland, 2014-2015.

Summer Schools

• Oxford Machine Learning Summer School (OxML), 2022.
• Global School on Empirical Research Methods (GSERM), St. Gallen, 2020.
• 3rd International Summer School on Deep Learning (DeepLearn) 2019, Warsaw, Poland.

Honors, Grants, and Awards

• HSG Impact Award 2023 for “Hyper-Representations: Learning from Populations of Neural Networks”.
• Google Research Scholar Award for “Hyper-Representations: Learning from Populations of Neural Networks”, PI: Damian Borth, in 2022/2023.
• DAAD/Voss Promos Scholorship for an engineering internship in Shanghai, China, in 2015/2016.
• Germany Scholarship (’Deutschlandstipendium’) in the academic year 2014/2015.
• RWTH Dean’s List (best 5% of students in a year) in the academic years 2012/2013 and 2014/2015.
• Erasmus+ DAAD Scholarship for an exchange to Aalto Univeristy, Helsinki, Finland in the academic year 2014/2015.

Review Activities

• Review for the Conference on Neural Information Processing Systems (NeurIPS) 2022, Datasets and Benchmarks.
• Review for Winter Conference on Applications of Computer Vision (WACV) 2023, The Computer Vision Foundation.

Work experience

• WSL Institute for Snow and Avalanche Research, Davos, Switzerland. 2018-2019.
  • Research Internship, Snowphysics Group.
  • Project on simulation of energy and mass transfer in snowpack in collaboration with the Aachen Institute for Advanced Computer Engineering Science (AICES).
  • Implementation of coupled, nonlinear FEM simulations in fenics; investigation of dynamic stability.
• Computational Analysis of Technical Systems (CATS), RWTH Aachen. 2016-2018.
  • Research Assistant, Fluid-Structure Interaction Group.
  • Code contribution to a compressible flow solver in fortran/
  • Implementation of methods for shock capturing and heat-flux in fluid-structure-interaction.
• Siemens Shanghai, China and Mülheim, German. 2015-2016.
  • Internship, Large Gas Turbine Division
  • Development of a thermodynamic model to predict water condensation in fuel gas pipes of dual-fuel gas turbines. to prevent catastrophic blow-off.
  • Support of development and evaluation of auxiliary systems for large gas turbines.
• Institute of Automatic Control (IRT), RWTH Aachen. 2013-2014.
  • Research Assistant
  • Development of thermal component-wise models of a hybrid vehicle in modelica.
  • Design of PID and model-predicitve controllers of the heat system model.

Skills

• Coding
  • Python (proficient)
  • C (past experience)
  • C++ (past experience)
  • fortran (past experience)
  • Matlab (proficient)
  • Git (proficient)
  • Unix (proficient)
• Machine Learning Pipeline
  • pytorch: core ML (proficient)
  • ray / tune: parallelization, hyperparameter optimization (proficient)
  • wandb, tensorboard: monitoring (proficient)
• Scientific Python
  • Pandas (proficient)
  • Numpy (proficient)
  • Scikit: baselines (proficient)
• Languages
  • German (mother tongue)
  • English (fluent)
  • French (basic proficiency)

Publications

On water vapor transport in snowpack models: Comparison of existing schemes, numerical requirements and the role of non-local advection.

Schürholt et al., 2019. "On water vapor transport in snowpack models: Comparison of existing schemes, numerical requirements and the role of non-local advection." EGU General Assembly 2019.

An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks

Schürholt et al., 2021. "An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks." Arxiv 2021.

Elements of future snowpack modeling – Part 1: A physical instability arising from the nonlinear coupling of transport and phase changes

Schürholt et al., 2022. "Elements of future snowpack modeling – Part 1: A physical instability arising from the nonlinear coupling of transport and phase changes." The Cryosphere 2022.

Predicting basin stability of power grids using graph neural networks

Nauck et al., 2022. "Predicting basin stability of power grids using graph neural networks." New Journal of Physics 2022.

Dynamic stability of power grids–new datasets for Graph Neural Networks

Nauck et al., 2022. "Dynamic stability of power grids--new datasets for Graph Neural Networks." Arxiv 2022.

Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction

Schürholt et al., 2021. "Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction." NeurIPS 2021.

Hyper-Representation for Pre-Training and Transfer Learning

Schürholt et al., 2022. "Hyper-Representation for Pre-Training and Transfer Learning." ICML Pretraining Workshop 2022.

Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights

Schürholt et al., 2022. "Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights." NeurIPS 2022.

Model Zoos: A Dataset of Diverse Populations of Neural Network Models

Schürholt et al., 2022. "Model Zoos: A Dataset of Diverse Populations of Neural Network Models." NeurIPS 2022.

Towards dynamic stability analysis of sustainable power grids using graph neural networks.

Nauck et al., 2022. "Towards dynamical stability analysis of sustainable power grids using Graph Neural Networks." NeurIPS 2022 Workshop on Tackling Climate Change with Machine Learning 2022.

Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models

Honegger et al., 2023. "Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models." ICLR Workshop on Sparsity in Neural Networks 2023.

Teaching

Teaching Assistance, Chair of Artificial Intelligence and Machine Learning

Student Supervision