Jakob Heiss

According to our database, Jakob Heiss authored at least 8 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Extending Path-Dependent NJ-ODEs to Noisy Observations and a Dependent Observation Framework.

William Andersson, Jakob Heiss, Florian Krach, Josef Teichmann

Trans. Mach. Learn. Res., 2024

Machine Learning-Powered Combinatorial Clock Auction.

Ermis Nikiforos Soumalias, Jakob Weissteiner, Jakob Heiss, Sven Seuken

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

How (Implicit) Regularization of ReLU Neural Networks Characterizes the Learned Function - Part II: the Multi-D Case of Two Layers with Random First Layer.

Jakob Heiss, Josef Teichmann, Hanna Wutte

CoRR, 2023

Bayesian Optimization-Based Combinatorial Assignment.

Jakob Weissteiner, Jakob Heiss, Julien Siems, Sven Seuken

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment.

Jakob Weissteiner, Jakob Heiss, Julien Siems, Sven Seuken

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, 2022

NOMU: Neural Optimization-based Model Uncertainty.

Jakob Heiss, Jakob Weissteiner, Hanna S. Wutte, Sven Seuken, Josef Teichmann

Proceedings of the International Conference on Machine Learning, 2022

2021

Infinite wide (finite depth) Neural Networks benefit from multi-task learning unlike shallow Gaussian Processes - an exact quantitative macroscopic characterization.

Jakob Heiss, Josef Teichmann, Hanna Wutte

CoRR, 2021

2019

How implicit regularization of Neural Networks affects the learned function - Part I.

Jakob Heiss, Josef Teichmann, Hanna Wutte

CoRR, 2019