mlsanityData to 7 Oct 2026

Maximum Likelihood Uncertainty Estimation: Robustness to Outliers

arXiv 2202.03870 ↗First posted 3 Feb 2022cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

We benchmark the robustness of maximum likelihood based uncertainty estimation methods to outliers in training data for regression tasks. Outliers or noisy labels in training data results in degraded performances as well as incorrect estimation of uncertainty. We propose the use of a heavy-tailed distribution (Laplace distribution) to improve the robustness to outliers. This property is evaluated using standard regression benchmarks and on a high-dimensional regression task of monocular depth estimation, both containing outliers. In particular, heavy-tailed distribution based maximum likelihood provides better uncertainty estimates, better separation in uncertainty for out-of-distribution data, as well as better detection of adversarial attacks in the presence of outliers.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 3 Feb 2022.

Builds on

27 of 45 references.

References · 27

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  7. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  8. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 411
  9. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  10. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 368
  11. 2019Deep Evidential Regressioncited by 354
  12. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
15 more
  1. 2015Scalable Bayesian Optimization Using Deep Neural Networkscited by 284
  2. 2017A General and Adaptive Robust Loss Functioncited by 236
  3. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  4. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171
  5. 2018Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Samplingcited by 166
  6. 2019Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networkscited by 158
  7. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  8. 2019Image Classification with Deep Learning in the Presence of Noisy Labels: A Surveycited by 101
  9. 2014Manifold Gaussian Processes for Regressioncited by 79
  10. 2019Analyzing the Role of Model Uncertainty for Electronic Health Recordscited by 41
  11. 2018Safely Entering the Deep: A Review of Verification and Validation for Machine Learning and a Challenge Elicitation in the Automotive Industrycited by 38
  12. 2021On the Robustness of Monte Carlo Dropout Trained with Noisy Labelscited by 11
  13. 2018DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Modelcited by 8
  14. 2017Robust and Accurate Inference via a Mixture of Gaussian and Student's t Errorscited by 1
  15. 2020Towards Using Probabilistic Models to Design Software Systems with Inherent Uncertaintycited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 1.

6 papers.

  1. 2023A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimationcited by 9
  2. 2023Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distributioncited by 5
  3. 2024Robust Long-Range Perception Against Sensor Misalignment in Autonomous Vehiclescited by 5
  4. 2024A Deep Learning Approach to Estimate Canopy Height and Uncertainty by Integrating Seasonal Optical, SAR and Limited GEDI LiDAR Data over Northern Forestscited by 1
  5. 2023Probabilistic MIMO U-Net: Efficient and Accurate Uncertainty Estimation for Pixel-wise Regressioncited by 0
  6. 2025Fundamentals of Regressioncited by 0