Likelihood-ratio-based confidence intervals for neural networks
Not on the map. Why?
Abstract (arXiv)
This paper introduces a first implementation of a novel likelihood-ratio-based approach for constructing confidence intervals for neural networks. Our method, called DeepLR, offers several qualitative advantages: most notably, the ability to construct asymmetric intervals that expand in regions with a limited amount of data, and the inherent incorporation of factors such as the amount of training time, network architecture, and regularization techniques. While acknowledging that the current implementation of the method is prohibitively expensive for many deep-learning applications, the high cost may already be justified in specific fields like medical predictions or astrophysics, where a reliable uncertainty estimate for a single prediction is essential. This work highlights the significant potential of a likelihood-ratio-based uncertainty estimate and establishes a promising avenue for future research.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 45 references that are in the map. First posted on arXiv 4 Aug 2023.
Builds on
21 of 45 references.
References · 21
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
- 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
- 2018On Lazy Training in Differentiable Programmingcited by 675
- 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
9 more
- 2017Concrete Dropoutcited by 227
- 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
- 2020Hyperparameter Ensembles for Robustness and Uncertainty Quantificationcited by 150
- 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
- 2019Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensemblescited by 30
- 2022The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regressioncited by 28
- 2022Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrappingcited by 19
- 2022Confident Neural Network Regression with Bootstrapped Deep Ensemblescited by 3
- 2022The Implicit Delta Methodcited by 1
Built on by
Citing papers per year: 2025: 1.
1 paper.