650 citations · 759 across the 14 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021
Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise
Jannik Schmitt, Stefan Roth
To adopt neural networks in safety critical domains, knowing whether we can trust their predictions is crucial. Bayesian neural networks (BNNs) provide uncertainty estimates by ave…
cs.LG2020★ 1 cited
Normalizing Flows with Multi-Scale Autoregressive Priors
Shweta Mahajan, Apratim Bhattacharyya, Mario Fritz +2
Flow-based generative models are an important class of exact inference models that admit efficient inference and sampling for image synthesis. Owing to the efficiency constraints o…