Reference-Tail Trust:Certified Probability Floors for Learned Updates Inside a Deployed Network
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/VKHS/RTT
Sources
- Pay Only for Disagreement: Certified No-Regression Verdicts for Model Updates with Matching Label-Complexity Bounds
- Conformal Policy Control
- Proximal Policy Optimization Algorithms
- Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
- Certifying Model Upgrades with Slice-Wise Non-Regression and Incumbent Fallback
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