no code implementations • 18 Sep 2023 • Maximilian Coblenz, Oliver Grothe, Fabian Kächele
By sampling from the latent space of an autoencoder and decoding the latent space samples to the original data space, any autoencoder can simply be turned into a generative model.
1 code implementation • 18 Apr 2023 • Mira Watermeyer, Thomas Möbius, Oliver Grothe, Felix Müsgens
The hybrid model generates both conventional point predictions and probabilistic forecasts, providing a comprehensive understanding of the market landscape.
no code implementations • 21 Feb 2023 • Thomas Möbius, Mira Watermeyer, Oliver Grothe, Felix Müsgens
These biases and high errors affect the quality of energy system models.
1 code implementation • 21 Apr 2022 • Oliver Grothe, Fabian Kächele, Fabian Krüger
Modeling price risks is crucial for economic decision making in energy markets.
1 code implementation • ICLR 2022 • Nils Koster, Oliver Grothe, Achim Rettinger
Through this extension and adaptations of initialization methods, we achieve a pruning rate of up to 99%, while still matching or exceeding the performance of various baseline and previous models.