1 citations · 1 across the 5 of their papers we have counts for
5 papers
AdamMCMC: Combining Metropolis Adjusted Langevin with Momentum-based Optimization
Sebastian Bieringer, Gregor Kasieczka, Maximilian F. Steffen +1
Uncertainty estimation is a key issue when considering the application of deep neural network methods in science and engineering. In this work, we introduce a novel algorithm that…
The surrogate Gibbs-posterior of a corrected stochastic MALA: Towards uncertainty quantification for neural networks
Sebastian Bieringer, Gregor Kasieczka, Maximilian F. Steffen +1
MALA is a popular gradient-based Markov chain Monte Carlo method to access the Gibbs-posterior distribution. Stochastic MALA (sMALA) scales to large data sets, but changes the targ…
Estimating a multivariate Lévy density based on discrete observations
Maximilian F. Steffen
Existing results for the estimation of the Lévy measure are mostly limited to the onedimensional setting. We apply the spectral method to multidimensional Lévy processes in order t…
PAC-Bayes Bounds for High-Dimensional Multi-Index Models with Unknown Active Dimension
Maximilian F. Steffen
The multi-index model with sparse dimension reduction matrix is a popular approach to circumvent the curse of dimensionality in a high-dimensional regression setting. Building on t…
A PAC-Bayes oracle inequality for sparse neural networks
Maximilian F. Steffen, Mathias Trabs
We study the Gibbs posterior distribution for sparse deep neural nets in a nonparametric regression setting. The posterior can be accessed via Metropolis-adjusted Langevin algorith…