NOMU: Neural Optimization-based Model Uncertainty J Heiss, J Weissteiner, H Wutte, S Seuken, J Teichmann International Conference on Machine Learning (ICML'22), 8708-8758, 2022 | 19 | 2022 |
Bayesian Optimization-based Combinatorial Assignment J Weissteiner, J Heiss, J Siems, S Seuken AAAI Conference on Artificial Intelligence (AAAI'23), 2022 | 14 | 2022 |
How Implicit Regularization of ReLU Neural Networks Characterizes the Learned Function--Part I: the 1-D Case of Two Layers with Random First Layer J Heiss, J Teichmann, H Wutte arXiv preprint arXiv:1911.02903, 2019 | 11 | 2019 |
Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment J Weissteiner, J Heiss, J Siems, S Seuken International Joint Conference on Artificial Intelligence (IJCAI'22), 541-548, 2022 | 10 | 2022 |
How (Implicit) Regularization of ReLU Neural Networks Characterizes the Learned Function--Part II: the Multi-D Case of Two Layers with Random First Layer J Heiss, J Teichmann, H Wutte arXiv preprint arXiv:2303.11454, 2023 | 3 | 2023 |
How Infinitely Wide Neural Networks Benefit from Multi-task Learning-an Exact Macroscopic Characterization J Heiss, J Teichmann, H Wutte ETH Zurich, 2022 | 3* | 2022 |
Machine Learning-powered Combinatorial Clock Auction EN Soumalias, J Weissteiner, J Heiss, S Seuken Proceedings of the AAAI Conference on Artificial Intelligence 38 (9), 9891-9900, 2024 | | 2024 |
Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework W Andersson, J Heiss, F Krach, J Teichmann arXiv preprint arXiv:2307.13147, 2023 | | 2023 |
Reducing the number of neurons of Deep ReLU Networks based on the current theory of Regularization J Heiss, A Stockinger, J Teichmann | | 2020 |