Maximus Mutschler

According to our database, Maximus Mutschler authored at least 7 papers between 2019 and 2023.

Collaborative distances:

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

2023

Empirics-based Line Searches for Deep Learning.

Maximus Mutschler

PhD thesis, 2023

2022

What to expect of hardware metric predictors in NAS.

Kevin Alexander Laube, Maximus Mutschler, Andreas Zell

Proceedings of the International Conference on Automated Machine Learning, 2022

2021

Using a one dimensional parabolic model of the full-batch loss to estimate learning rates during training.

Maximus Mutschler, Andreas Zell

CoRR, 2021

Empirically Explaining SGD from a Line Search Perspective.

Maximus Mutschler, Andreas Zell

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2021, 2021

2020

A straightforward line search approach on the expected empirical loss for stochastic deep learning problems.

Maximus Mutschler, Andreas Zell

CoRR, 2020

Parabolic Approximation Line Search for DNNs.

Maximus Mutschler, Andreas Zell

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

PAL: A fast DNN optimization method based on curvature information.

Maximus Mutschler, Andreas Zell

CoRR, 2019