Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
On water vapor transport in snowpack models: Comparison of existing schemes, numerical requirements and the role of non-local advection.
Published in European Geosciences Union (EGU) General Assembly 2019, 2019
In this work, we investigate the numerical properties of coupled mass and energy equations of snow pack.
Recommended citation: 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. https://search.ebscohost.com/login.aspx?direct=true&profile=ehost&scope=site&authtype=crawler&jrnl=10297006&AN=140480720&h=OIy4BTnTfn8MswNyU913MD0Xo04OcI6gH7aYV7TAye0vFuoL6%2FrVJwyn3PeyJIlnbWBhd97x9Iezqwkcgn5k0w%3D%3D&crl=c
An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks
Published in Arxiv, 2021
In this paper, we investigate the weight space of populations of Neural Networks.
Recommended citation: Schürholt et al., 2021. "An Investigation of the Weight Space to Monitor the Training Progress of Neural Networks." Arxiv 2021. https://arxiv.org/abs/2006.10424
Elements of future snowpack modeling – Part 1: A physical instability arising from the nonlinear coupling of transport and phase changes
Published in The Cryosphere, 2022
This paper studies the effect of numerical instabilities of coupled heat and mass equations of ice in snow pack.
Recommended citation: 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. https://tc.copernicus.org/articles/16/903/2022/
Predicting basin stability of power grids using graph neural networks
Published in New Journal of Physics, 2022
This paper investigats the applicability of Graph Neural Networks to predict dynamic stability of power grids.
Recommended citation: Nauck et al., 2022. "Predicting basin stability of power grids using graph neural networks." New Journal of Physics 2022. https://iopscience.iop.org/article/10.1088/1367-2630/ac54c9/pdf
Dynamic stability of power grids–new datasets for Graph Neural Networks
Published in Arxiv, 2022
We generate new datasets based on dynamical simulations of power grids as a challenge for Graph Neural Networks and include benchmark performances on different tasks including out-of-distribution generalization.
Recommended citation: Nauck et al., 2022. "Dynamic stability of power grids--new datasets for Graph Neural Networks." Arxiv 2022. https://arxiv.org/abs/2206.06369
Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction
Published in Neural Information Processing Systems (NeurIPS) 2021, 2022
This paper proposes to learn self-supervised representations of the weights of populations of NN models using novel data augmentations and an adapted transformer architecture.
Recommended citation: Schürholt et al., 2021. "Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction." NeurIPS 2021. https://arxiv.org/abs/2110.15288
Hyper-Representation for Pre-Training and Transfer Learning
Published in International Conference on Machine Learning (ICML) Pretraining Workshop 2022, 2022
In this paper, we extend hyper-representations for generative use to sample neural network weights for initialization and transfer learning.
Recommended citation: Schürholt et al., 2022. "Hyper-Representation for Pre-Training and Transfer Learning." ICML Pretraining Workshop 2022. https://arxiv.org/abs/2207.10951
Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights
Published in Neural Information Processing Systems (NeurIPS) 2022, 2022
In this paper, we extend hyper-representations for generative use to sample neural network weights for initialization, ensembling and transfer learning.
Recommended citation: Schürholt et al., 2022. "Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights." NeurIPS 2022. https://arxiv.org/abs/2209.14733
Model Zoos: A Dataset of Diverse Populations of Neural Network Models
Published in Neural Information Processing Systems (NeurIPS) 2022 Datasets and Benchmarks Track, 2022
To enable the investigation of populations of neural network models, we release a novel dataset of diverse model zoos with this work.
Recommended citation: Schürholt et al., 2022. "Model Zoos: A Dataset of Diverse Populations of Neural Network Models." NeurIPS 2022. https://arxiv.org/abs/2209.14764
Towards dynamic stability analysis of sustainable power grids using graph neural networks.
Published in NeurIPS 2022 Climate Change AI Workshop, 2022
We generate new datasets based on dynamical simulations of power grids as a challenge for Graph Neural Networks and include benchmark performances on different tasks including out-of-distribution generalization.
Recommended citation: 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. https://www.climatechange.ai/papers/neurips2022/16
Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models
Published in ICLR Workshop on Sparsity in Neural Networks 2023, 2023
In this paper, we apply common sparsification methods on population of Neural Networks and analyze their performance and relation between sparse and full models.
Recommended citation: Honegger et al., 2023. "Sparsified Model Zoo Twins: Investigating Populations of Sparsified Neural Network Models." ICLR Workshop on Sparsity in Neural Networks 2023. https://arxiv.org/abs/2304.13718
Eurosat Model Zoo: A Dataset and Benchmark on Populations of Neural Networks and Its Sparsified Model Twins
Published in 2023 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2023
Here, we study the benefits of populations of small models for remote sensing applications.
Recommended citation: Honegger et al., 2023. "Eurosat Model Zoo: A Dataset and Benchmark on Populations of Neural Networks and Its Sparsified Model Twins." IGARSS 2023. https://ieeexplore.ieee.org/abstract/document/10283060
Toward dynamic stability assessment of power grid topologies using graph neural networks
Published in Chaos: An Interdisciplinary Journal of Nonlinear Science, 2023
This paper investigats the applicability of Graph Neural Networks to predict dynamic stability of power grids.
Recommended citation: Nauck et al., 2023. "Toward dynamic stability assessment of power grid topologies using graph neural networks." Chaos: An Interdisciplinary Journal of Nonlinear Science 2023. https://pubs.aip.org/aip/cha/article/33/10/103103/2914062
MD tree: a model-diagnostic tree grown on loss landscape
Published in International Conference on Machine Learning, 2024
Here, we propose methods to use loss landscape metrics to diagnose failure models in trained models.
Recommended citation: Zhou et al., 2024. "MD tree: a model-diagnostic tree grown on loss landscape." ICML 2024. https://openreview.net/forum?id=teHPKqjX8q&referrer=%5Bthe%20profile%20of%20Konstantin%20Sch%C3%BCrholt%5D(%2Fprofile%3Fid%3D~Konstantin_Sch%C3%BCrholt1)
Towards Scalable and Versatile Weight Space Learning
Published in International Conference on Machine Learning, 2024
In this paper, we propose methods to scale weight space learning approaches to large models of varying architectures.
Recommended citation: Schürholt et al., 2024. "Towards Scalable and Versatile Weight Space Learning." ICML 2024. https://arxiv.org/abs/2406.09997
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching Assistance, Chair of Artificial Intelligence and Machine Learning
Bachelor and Master level courses, University of St. Gallen, Department of Computer Science, 2019
As a PhD student, I regularly support the Chair as TA for our own Machine Learning courses, as well as the school for general computer science classes.
Student Supervision
Supervision, University of St. Gallen, Department of Computer Science, 2021
As part of my teaching, I regularly co-supervise bachelor, master and project theses on topics related to my research.