Conformal Policy Control
Drew Prinster, Clara Fannjiang, Ji Won Park, Kyunghyun Cho, Anqi Liu, Suchi Saria, Samuel Stanton
cs.AI, cs.LG, math.ST, stat.ML, stat.TH
Submitted: 2026-08-19
Updated: 2026-08-20
Comments: International Conference on Machine Learning (ICML), 2026. v4: Revised CPC theory to (a) show enforced smoothness for likelihood-ratio control parameter and (b) for general control parameter, assume smoothness only of constrained policy $π_t^{(β)}$ w.r.t. $β$ (rather than of $(l_i - α)\cdotπ_t^{(β)}$ or of conformal weights)
Code: https://github.com/samuelstanton/conformal-policy-control
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Optimized Conformal Selection: Powerful Selective Inference After Conformity Score Optimization
- Unifying Different Theories of Conformal Prediction
- Concrete Problems in AI Safety
- Beyond the training set: an intuitive method for detecting distribution shift in model-based optimization
- Conformal Prediction Sets Improve Human Decision Making
- Offline Model-Based Optimization: Comprehensive Review
- ACS: An interactive framework for conformal selection
- Conformal Prediction and Human Decision Making
- OLAPH: Improving Factuality in Biomedical Long-form Question Answering
- Conformal Linguistic Calibration: Trading-off between Factuality and Specificity
- Formal Verification and Control with Conformal Prediction
- Randomization Tests for Adaptively Collected Data
- Proximal Policy Optimization Algorithms
- Distribution-free risk assessment of regression-based machine learning algorithms
- Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control
- Conformalized Interactive Imitation Learning: Handling Expert Shift and Intermittent Feedback
- Conformalized Decision Risk Assessment
- Conformal Risk Training: End-to-End Optimization of Conformal Risk Control
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems