Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy

arXiv:2605.01632 · cs.LG · Submitted 2026-05-02 · Read on arXiv

cs.LG

Submitted: 2026-05-02

Updated: 2026-10-05

Code: https://github.com/EtherealEq/perturb-and-correct

Terminology

• Calibration — 3× in this paper · explained in 7 episodes
• Distribution Shift — 1× in this paper · explained in 7 episodes
• Redundancy — 1× in this paper · explained in 2 episodes

Sources

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• Gymnasium: A Standard Interface for Reinforcement Learning Environments
• BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
• OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks