Deterministic Variational Inference for Robust Bayesian Neural Networks

By Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner, José Miguel Hernández-Lobato, Alexander L. Gaunt. 2018

185 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks (2020, methodology): “We train these networks by following the procedure described by Meinke & Hein (2020) (Appendix C).”
Subspace Inference for Bayesian Deep Learning (2019, methodology): “The subspace methods outperform SGD and DVI on naval, concrete and yacht and are competitive on the other datasets.”
Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning (2020, background): “iction of an ensemble by a single neural network (Hinton et al., 2015; Balan et al., 2015; Tran et al., 2020), whereas fast dropout (Wang & Manning, 2013) and deterministic variational inference (Wu et al., 2018) allow to approximate the predictive distribution of speciﬁc stochastic computation ”
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges (2020, methodology): “[385] devised two methods to turn VB into a robust inference tool for BNNs.”
A survey of uncertainty in deep neural networks (2021, methodology): “1[20] 3[30] 4[149] 5[75] 6[213] 7[129] 8[63] 9[80] 10[150] 11[143] 12[84] 13[235] 14[145] 15[135] 16[146] 17[272]”
What Are Bayesian Neural Network Posteriors Really Like? (2021, methodology): “, 2019) and deterministic variational inference (DVI; Wu et al., 2018).”
Hierarchical Gaussian Process Priors for Bayesian Neural Network Weights (2020, background): “…area, and the main focuses of which are (i) improving the reparameterization gradient estimator to enable faster convergence [Miller et al., 2017, Wu et al., 2018], (ii) replacing the typical standard Normal prior, p(w) = N (w;0, I) by a structured prior that better models the structures present…”
Laplace Redux - Effortless Bayesian Deep Learning (2021, background): “[91] Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E.”
Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning (2019, background): “Wu et al. [2019] instead see the variance of ELBO estimates as the problem and introduce a deterministic alternative.”
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks (2019, background): “Despite BDL’s impact on a range of real-world applications and the flourish of recent ideas and inference techniques [11, 3, 8, 48, 50, 37], the development of the field itself is impeded by the lack of realistic benchmarks to guide research.”