← Back to all news
arXiv Statistics ML By Ayush Mittal, Dhruv Gupta

Calibrated for Which Policy? Conformal Uncertainty for Fixed World Models Under Intervention

Read the original on arXiv Statistics ML →

arXiv:2610. 35877v1 Announce Type: cross Abstract: Changing a deployment policy can invalidate a world model's uncertainty while leaving the physical transition mechanism and predictor unchanged.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

Related stories

arXiv AI
Jun 30

Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models

arXiv:2606. 30627v1 Announce Type: cross Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it is less likely to exploit imperfections in a learned reward model.

By Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary
reinforcement-learningsafety
More like this →
arXiv Machine Learning
Jun 9

A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Control

arXiv:2606. 08517v1 Announce Type: new Abstract: Selective predictors answer on confident inputs and abstain elsewhere; deploying one safely needs a single finite-sample certificate that simultaneously upper-bounds the selected risk, lower-bounds the acceptance probability $\pacc$ above a floor $\pmin$, and lower-bounds the deployment utility.

By Xiaoli Yu, Jiamiao Liu
More like this →
arXiv Machine Learning
Aug 26

Replicable Conformal Prediction

arXiv:2608.23638v1 Announce Type: cross Abstract: Two analysts who calibrate the same predictive model on independent samples will deploy different prediction sets every time, because the calibration...

By Marios Papamichalis, Regina Ruane, Theofanis Papamichalis
More like this →
arXiv Machine Learning
Sep 17

A Convergence Framework for Deep $V$-Learning: Error Propagation and Sharp Action-Gap Bounds

The paper presents a convergence framework for deep $V$‑learning over a finite horizon $H$, deriving explicit bounds on policy loss by decomposing the Bellman update error into six residuals. It shows how $L^s$ concentrability controls expected $L^1$ loss, quantifies the impact of shared sampling across horizon levels, and provides optimal and near‑optimal sample allocations for statistical error rates. The work also establishes sharp action‑gap bounds under a margin condition, transfers optimal‑gap results to frozen‑iterate gaps, and offers consistency guarantees for generative‑reset approximate‑ERM procedures with exact action scores.

By Yury Kolomeytsev
More like this →