Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Dold, Daniel"'
Autor:
Kook, Lucas, Kolb, Chris, Schiele, Philipp, Dold, Daniel, Arpogaus, Marcel, Fritz, Cornelius, Baumann, Philipp F., Kopper, Philipp, Pielok, Tobias, Dorigatti, Emilio, Rügamer, David
Neural network representations of simple models, such as linear regression, are being studied increasingly to better understand the underlying principles of deep learning algorithms. However, neural representations of distributional regression models
Externí odkaz:
http://arxiv.org/abs/2405.05429
Semi-structured regression models enable the joint modeling of interpretable structured and complex unstructured feature effects. The structured model part is inspired by statistical models and can be used to infer the input-output relationship for f
Externí odkaz:
http://arxiv.org/abs/2401.12950
Variational inference (VI) is a technique to approximate difficult to compute posteriors by optimization. In contrast to MCMC, VI scales to many observations. In the case of complex posteriors, however, state-of-the-art VI approaches often yield unsa
Externí odkaz:
http://arxiv.org/abs/2202.05650
The main challenge in Bayesian models is to determine the posterior for the model parameters. Already, in models with only one or few parameters, the analytical posterior can only be determined in special settings. In Bayesian neural networks, variat
Externí odkaz:
http://arxiv.org/abs/2106.00528