Sebastian Kassing

According to our database, Sebastian Kassing authored at least 9 papers between 2021 and 2024.

Collaborative distances:

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

2024

On the Existence of Minimizers in Shallow Residual ReLU Neural Network Optimization Landscapes.

Steffen Dereich, Arnulf Jentzen, Sebastian Kassing

SIAM J. Numer. Anal., 2024

Stochastic Modified Flows for Riemannian Stochastic Gradient Descent.

Benjamin Gess, Sebastian Kassing, Nimit Rana

SIAM J. Control. Optim., 2024

Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent.

Benjamin Gess, Sebastian Kassing, Vitalii Konarovskyi

J. Mach. Learn. Res., 2024

Polyak's Heavy Ball Method Achieves Accelerated Local Rate of Convergence under Polyak-Lojasiewicz Inequality.

Sebastian Kassing, Simon Weissmann

CoRR, 2024

2023

On the existence of optimal shallow feedforward networks with ReLU activation.

Steffen Dereich, Sebastian Kassing

CoRR, 2023

Convergence rates for momentum stochastic gradient descent with noise of machine learning type.

Benjamin Gess, Sebastian Kassing

CoRR, 2023

2022

On minimal representations of shallow ReLU networks.

Steffen Dereich, Sebastian Kassing

Neural Networks, 2022

2021

Stochastic approximation with a focus on machine learning applications.

Sebastian Kassing

PhD thesis, 2021

Convergence of stochastic gradient descent schemes for Lojasiewicz-landscapes.

Steffen Dereich, Sebastian Kassing

CoRR, 2021