Moritz Haas

According to our database, Moritz Haas authored at least 6 papers between 2022 and 2025.

Collaborative distances:

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

2025

On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling.

Moritz Haas, Sebastian Bordt, Ulrike von Luxburg, Leena Chennuru Vankadara

CoRR, May, 2025

2024

μ P²: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling.

Moritz Haas, Jin Xu, Volkan Cevher, Leena Chennuru Vankadara

CoRR, 2024

On Feature Learning in Structured State Space Models.

Leena Chennuru Vankadara, Jin Xu, Moritz Haas, Volkan Cevher

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

μP²: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling.

Moritz Haas, Jin Xu, Volkan Cevher, Leena Chennuru Vankadara

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension.

Moritz Haas, David Holzmüller, Ulrike von Luxburg, Ingo Steinwart

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Pitfalls of Climate Network Construction: A Statistical Perspective.

Moritz Haas, Bedartha Goswami, Ulrike von Luxburg

CoRR, 2022