Open
Description
Last Update Date: 2020/03/22
Tutorials and Seminars
- Andrew Gordon Wilson on Bayesian deep learning; Primer: Pavel Izmailov and Polina Kirichenko. Broad Institute of MIT and Harvard. [Slides].
- Bayesian ML/DL Playlist by Bayesian Methods Research Group from Moscow, Russia.
PhD Thesis
- Bayesian Method for Adaptive Models. David J.C. MacKay (1992)
- Bayesian Learning for Neural Networks. Lecture Notes in Statistics. Neal, R. M. (1996)
- Uncertainty in Deep Learning. Yarin Gal (2016)
Uncertainty
2015
- Weight Uncertainty in Neural Networks by Charles Blundell. ICML 2015.
2016
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning by Yarin Gal. ICML 2016.
2017
- On Calibration of Modern Neural Networks by Chuan Guo et al. ICML 2017.
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles by Lakshminarayanan et al. NIPS 2017.
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? by Alex Kendall & Yarin Gal. NIPS 2017.
2018
- Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics by Alex Kendall et al. CVPR 2018.
- Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow by Ilg et al. ECCV 2018.
- Accurate Uncertainties for Deep Learning Using Calibrated Regression by Volodymyr Kuleshov et al. ICML 2018.
- Predictive Uncertainty Estimation via Prior Networks by Andrey Malinin et al. NeurIPS 2018.
2019
- Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers by Geifman et al. ICLR 2019.
- Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem by Matthias Hein et al. CVPR 2019.
- Noise Contrastive Priors for Functional Uncertainty by Danijar Hafner et al. UAI 2019.
- Sampling-free Uncertainty Estimation in Gated Recurrent Units with Applications to Normative Modeling in Neuroimaging by Seong Jae Hwang et al. UAI 2019.
- Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation by Janis Postels et al. ICCV 2019.
- Can you trust your model's uncertainty? Evaluating predictive uncertainty under dataset shift by Yaniv Ovadia et al. NeurIPS 2019.
- A Simple Baseline for Bayesian Uncertainty in Deep Learning by Maddox et al. NeurIPS 2019.
- Single-Model Uncertainties for Deep Learning by Natasa Tagasovska & David Lopez-Paz. NeurIPS 2019.
- Verified Uncertainty Calibration by Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019.
2020
- Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning by Arsenii Ashukha, +2, Dmitry Vetrov. ICLR 2020.
- Scalable Uncertainty for Computer Vision with Functional Variational Inference by Carvalho et al. CVPR 2020.
Generalization
2017
- Stochastic Gradient Descent as Approximate Bayesian Inference by Stephan Mandt et al. JMLR 2017.
2018
- Averaging Weights Leads to Wider Optima and Better Generalization by Pavel Izmailov, +2, Dmitry Vetrov, Andrew Gordon Wilson. UAI 2018.
2019
- Understanding Priors in Bayesian Neural Networks at the Unit Level by Vladimirova et al. ICML 2019.
- The Deep Weight Prior by Andrei Atanov, +2, Dmitry Vetrov, Max Welling. ICLR 2019.
- Functional Variational Bayesian Neural Networks by Sun, +2, Roger Grosse. ICLR 2019.
- Subspace Inference for Bayesian Deep Learning by Pavel Izmailov, +3, Dmitry Vetrov, Andrew Gordon Wilson. UAI 2019.
- Practical Deep Learning with Bayesian Principles by Kazuki Osawa & Emtiyaz Khan. NeurIPS 2019.
- Approximate Inference Turns Deep Networks into Gaussian Processes by Emtiyaz Khan et al. NeurIPS 2019.
2020
- Bayesian Deep Learning and a Probabilistic Perspective of Generalization by Andrew Gordon Wilson.
- Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited by Wesley J. Maddox, +1, Andrew Gordon Wilson.