Credal Machine Learning for Risk-Averse Decision Making
cs.LG, stat.ML
Submitted: 2026-10-08
Updated: 2026-10-08
Code: https://github.com/timoverse/credal-ml-risk-averse-dm
Terminology
Sources
- Credal Bayesian Deep Learning
- Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination
- The intersection probability: betting with probability intervals
- Learning Models with Uniform Performance via Distributionally Robust Optimization
- Efficient Credal Prediction through Decalibration
- Possibilistic Predictive Uncertainty for Deep Learning
- Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
- MedMNIST-C: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions
- Statistical Learning with Conditional Value at Risk
- Learning Credal Ensembles via Distributionally Robust Optimization
- MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks