mlsanityData to 7 Oct 2026

MaxEnt Loss: Constrained Maximum Entropy for Calibration under Out-of-Distribution Shift

arXiv 2310.17159 ↗First posted 26 Oct 2023cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We present a new loss function that addresses the out-of-distribution (OOD) calibration problem. While many objective functions have been proposed to effectively calibrate models in-distribution, our findings show that they do not always fare well OOD. Based on the Principle of Maximum Entropy, we incorporate helpful statistical constraints observed during training, delivering better model calibration without sacrificing accuracy. We provide theoretical analysis and show empirically that our method works well in practice, achieving state-of-the-art calibration on both synthetic and real-world benchmarks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

32 of 56 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  10. 2016End to End Learning for Self-Driving Carscited by 1,000
  11. 2019When Does Label Smoothing Help?cited by 985
  12. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
20 more
  1. 2019Measuring Calibration in Deep Learningcited by 443
  2. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  3. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  4. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  5. 2017Functional Map of the Worldcited by 338
  6. 2019Verified Uncertainty Calibrationcited by 307
  7. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  8. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  9. 2020MetNet: A Neural Weather Model for Precipitation Forecastingcited by 128
  10. 2020Improving model calibration with accuracy versus uncertainty optimizationcited by 123
  11. 2020Calibration of Neural Networks using Splinescited by 97
  12. 2021Soft Calibration Objectives for Neural Networkscited by 89
  13. 2015Posterior calibration and exploratory analysis for natural language processing modelscited by 75
  14. 2018Maximum-Entropy Fine-Grained Classificationcited by 64
  15. 2022PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functionscited by 62
  16. 2020Post-hoc Uncertainty Calibration for Domain Drift Scenarioscited by 61
  17. 2020Transferable Calibration with Lower Bias and Variance in Domain Adaptationcited by 41
  18. 2022Robust Calibration with Multi-domain Temperature Scalingcited by 39
  19. 2023Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibrationcited by 19
  20. 2021Morphset:Augmenting categorical emotion datasets with dimensional affect labels using face morphingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 1.

6 papers.

  1. 2025EOOD: Entropy-based Out-of-distribution Detectioncited by 5
  2. 2025ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Ratecited by 3
  3. 2025An Entropic Metric for Measuring Calibration of Machine Learning Modelscited by 2
  4. 2025Addressing Label Shift in Distributed Learning via Entropy Regularizationcited by 1
  5. 2025Target-Agnostic Calibration under Distribution Shift with Frequency-Aware Gradient Rectificationcited by 1
  6. 2026Autonomous Drift Learning in Data Streams: A Unified Perspectivecited by 0