arXiv AI
Human-Centered Learning Mechanics: Observable Entropy Control under Protected-Risk Constraints
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Aug 13
The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification
arXiv:2608. 11243v1 Announce Type: new Abstract: We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.
arXiv AI
Jul 7
Safe RLHF Beyond Expectation: Stochastic Dominance for Universal Spectral Risk Control
arXiv:2603. 10938v2 Announce Type: replace-cross Abstract: Safe Reinforcement Learning from Human Feedback (RLHF) typically enforces safety through expected cost constraints, but the expectation captures only a single statistic of the cost distribution and fails to account for distributional uncertainty, particularly under heavy tails or rare catastrophic events.
arXiv Machine Learning
Jul 28
Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety
arXiv:2607. 22929v1 Announce Type: new Abstract: A short fine-tuning run can undo the safety guards of an open-weight model---retraining a refusal-trained assistant to aid weapons development or produce hate speech.
arXiv Machine Learning
Jun 15
Utility-Constrained Policy Optimization
arXiv:2606. 14029v1 Announce Type: new Abstract: Constrained MDPs (CMDPs) are a widely adopted framework for incorporating safety into RL agents; however, the framework does not support risk-sensitive constraints.
arXiv Machine Learning
Aug 20
Contrasting Cost-Agnostic and Cost-Sensitive Losses under Limited Model Capacity via $\mathcal H$-consistency
The paper investigates the difference between cost‑agnostic and cost‑sensitive loss functions when model capacity is limited. It shows that, unlike in ideal infinite‑capacity settings, optimizing a cost‑sensitive objective can yield a strictly better downstream decision than post‑processing a cost‑agnostic model. The authors prove this gap under a hypothesis class that can recover the optimal decision boundary but not the optimal cost‑agnostic hypothesis, and provide a simple example and empirical evidence on UCI datasets with simple models.
arXiv Machine Learning
Sep 11
Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations
arXiv:2609. 10866v1 Announce Type: new Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications.