Hanna Tseran

According to our database, Hanna Tseran authored at least 4 papers between 2021 and 2024.

Collaborative distances:

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

2024

Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape.

Kedar Karhadkar, Michael Murray, Hanna Tseran, Guido Montúfar

Trans. Mach. Learn. Res., 2024

2023

Expected Complexity and Gradients of Deep Maxout Neural Networks and Implications to Parameter Initialization

Hanna Tseran

PhD thesis, 2023

Expected Gradients of Maxout Networks and Consequences to Parameter Initialization.

Hanna Tseran, Guido Montúfar

Proceedings of the International Conference on Machine Learning, 2023

2021

On the Expected Complexity of Maxout Networks.

Hanna Tseran, Guido Montúfar

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021