Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

The Epistemic Uncertainty Hole: an issue of Bayesian Neural Networks (2407.01985v1)

Published 2 Jul 2024 in stat.ML and cs.LG

Abstract: Bayesian Deep Learning (BDL) gives access not only to aleatoric uncertainty, as standard neural networks already do, but also to epistemic uncertainty, a measure of confidence a model has in its own predictions. In this article, we show through experiments that the evolution of epistemic uncertainty metrics regarding the model size and the size of the training set, goes against theoretical expectations. More precisely, we observe that the epistemic uncertainty collapses literally in the presence of large models and sometimes also of little training data, while we expect the exact opposite behaviour. This phenomenon, which we call "epistemic uncertainty hole", is all the more problematic as it undermines the entire applicative potential of BDL, which is based precisely on the use of epistemic uncertainty. As an example, we evaluate the practical consequences of this uncertainty hole on one of the main applications of BDL, namely the detection of out-of-distribution samples

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. A comparison of uncertainty estimation approaches in deep learning components for autonomous vehicle applications. In Proceedings of the IJCAI-PRICAI-20 Workshop on Artificial Intelligence Safety, 2020.
  2. Weight uncertainty in neural networks. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, ICML’15, page 1613–1622. JMLR.org, 2015.
  3. Estimating risk and uncertainty in deep reinforcement learning. arXiv preprint arXiv:1905.09638, 2019.
  4. Yarin Gal. Uncertainty in Deep Learning. PhD thesis, University of Cambridge, 2016.
  5. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML’16, page 1050–1059. JMLR.org, 2016.
  6. Deep Bayesian active learning with image data. In Doina Precup and Yee Whye Teh, editors, Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 1183–1192. PMLR, 06–11 Aug 2017.
  7. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  8. Auto-encoding variational bayes. In Yoshua Bengio and Yann LeCun, editors, ICLR, 2014.
  9. Uncertainty quantification using bayesian neural networks in classification: Application to biomedical image segmentation. Comput. Stat. Data Anal., 142, 2020.
  10. Simple and scalable predictive uncertainty estimation using deep ensembles. In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017.
  11. David J. C. MacKay. A Practical Bayesian Framework for Backpropagation Networks. Neural Computation, 4(3):448–472, May 1992.
  12. Radford M. Neal. Bayesian Learning for Neural Networks, volume 118 of Lecture Notes in Statistics. Springer New York, New York, NY, 1996.
  13. Reading digits in natural images with unsupervised feature learning. In Workshop on Deep Learning and Unsupervised Feature Learning, 2011.
  14. Understanding measures of uncertainty for adversarial example detection. In Amir Globerson and Ricardo Silva, editors, Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial Intelligence, UAI 2018, Monterey, California, USA, August 6-10, 2018, pages 560–569. AUAI Press, 2018.
  15. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 15(1):1929–1958, jan 2014.
  16. Intriguing properties of neural networks. In Yoshua Bengio and Yann LeCun, editors, 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, 2014.
  17. Resmlp: Feedforward networks for image classification with data-efficient training. CoRR, abs/2105.03404, 2021.
  18. Bayesian deep learning and a probabilistic perspective of generalization. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS’20, Red Hook, NY, USA, 2020. Curran Associates Inc.
  19. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms, 2017.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Mohammed Fellaji (2 papers)
  2. Frédéric Pennerath (5 papers)
Citations (1)

Summary

We haven't generated a summary for this paper yet.

X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets