Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference

• URL: http://arxiv.org/abs/2606.00320v1
• Date: Fri, 29 May 2026 19:52:36 GMT
• Title: Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference
• Abstract summary: We present an online, distribution-free framework for controlling Conditional Value-at-Risk (CVaR)<n>Unlike classical risk control methods, our approach provides provable safety guarantees for a nonlinear tail risk functional under arbitrary data-generating processes.
• Score: 15.255874441202872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present an online, distribution-free framework for controlling the Conditional Value-at-Risk (CVaR), extending conformal tail risk control to non-stationary and adversarial environments. Unlike classical risk control methods, which rely on stationarity or linearity of expectation, our approach provides provable safety guarantees for a nonlinear tail risk functional under arbitrary data-generating processes that may drift or shift strategically over time. By leveraging deep connections between conformal tail risk control, online learning, and the variational representation of CVaR introduced by Rockafellar and Uryasev, we develop a novel procedure for online CVaR control with adversarial regret guarantees. The proposed method operates without assumptions on the underlying data-generating process, making it broadly applicable in modern high-stakes deployment settings. We prove that the realized empirical CVaR is asymptotically controlled at the target level, and that the resulting control is asymptotically tight up to a finite-sample conservatism gap. We demonstrate the effectiveness of our approach on portfolio risk management and toxicity mitigation for Large Language Models (LLMs), where rare but catastrophic failures dominate system risk.

Related papers

• Conformal Risk-Averse Decision Making with Optimized Certainty Equivalent Risk Control [31.006941545235396]
  We study risk-averse decision making in which an agent selects actions while being uncertain about the true system state.<n>We characterize the optimal policy under known distributions, and show that it reduces to a prediction set-based solution for the CVaR.<n>For unknown distributions, we develop a data-driven calibration strategy, based on a synthetic model for the likelihood and held-out calibration data.
  arXiv  Detail & Related papers  (2026-08-28T10:45:23Z)
• RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance [0.0]
  offline reinforcement learning enables policy learning from fixed datasets without additional environment interaction.<n>We propose RS-Diffuser, a risk-sensitive offline diffusion planning framework that combines diffusion-based trajectory generation with distributional value critics.<n>Experiments on risk-sensitive D4RL and risky robot navigation benchmarks demonstrate that RS-Diffuser achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-06-26T06:51:16Z)
• Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability [79.08785366532287]
  We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability.<n>We evaluate the approach in two safety-critical partially observable domains: automated glucose regulation and safety-constrained navigation.
  arXiv  Detail & Related papers  (2026-05-14T01:23:09Z)
• Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models [57.006252510102506]
  Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications.<n>We introduce a novel recovery-based shielding framework that enables safe RL with a provable safety lower bound for unknown and non-linear continuous dynamical systems.
  arXiv  Detail & Related papers  (2026-02-12T22:03:35Z)
• Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment [49.2305683068875]
  We propose Risk-aware Stepwise Alignment (RSA), a novel alignment method that incorporates risk awareness into the policy optimization process.<n> RSA mitigates risks induced by excessive model shift away from a reference policy, and it explicitly suppresses low-probability yet high-impact harmful behaviors.<n> Experimental results demonstrate that our method achieves high levels of helpfulness while ensuring strong safety.
  arXiv  Detail & Related papers  (2025-12-30T14:38:02Z)
• Conformal Risk Training: End-to-End Optimization of Conformal Risk Control [41.45834526675908]
  We introduce "conformal risk training," an end-to-end approach that differentiates through conformal OCE risk control during model training or fine-tuning.<n>Our method achieves provable risk guarantees while demonstrating significantly improved average-case performance over post-hoc approaches.
  arXiv  Detail & Related papers  (2025-10-09T19:05:45Z)
• Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning [4.8342038441006805]
  We propose a novel framework for optimizing static Spectral Risk Measures (SRM)<n>Our algorithms consistently outperform existing risk-sensitive methods in both online and offline environments across diverse domains.
  arXiv  Detail & Related papers  (2025-07-05T04:41:54Z)
• Risk-Averse Certification of Bayesian Neural Networks [70.44969603471903]
  We propose a Risk-Averse Certification framework for Bayesian neural networks called RAC-BNN.<n>Our method leverages sampling and optimisation to compute a sound approximation of the output set of a BNN.<n>We validate RAC-BNN on a range of regression and classification benchmarks and compare its performance with a state-of-the-art method.
  arXiv  Detail & Related papers  (2024-11-29T14:22:51Z)
• Localized Adaptive Risk Control [35.88667386998423]
  Localized Adaptive Risk Control (L-ARC) is an online calibration scheme that targets statistical localized risk guarantees. L-ARC is demonstrated via experiments to produce prediction sets with risk guarantees across different data subpopulations.
  arXiv  Detail & Related papers  (2024-05-13T17:48:45Z)
• Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction [55.77015419028725]
  We develop methods that permit valid control of risk when threshold and tradeoff parameters are chosen adaptively. Our methodology supports monotone and nearly-monotone risks, but otherwise makes no distributional assumptions.
  arXiv  Detail & Related papers  (2024-03-28T17:28:06Z)
• Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization [63.93275508300137]
  We introduce a novel risk-aware Counterfactual Learning To Rank method with theoretical guarantees for safe deployment. Our experimental results demonstrate the efficacy of our proposed method, which is effective at avoiding initial periods of bad performance when little data is available.
  arXiv  Detail & Related papers  (2023-04-26T15:54:23Z)
• Learning Disturbances Online for Risk-Aware Control: Risk-Aware Flight with Less Than One Minute of Data [33.7789991023177]
  Recent advances in safety-critical risk-aware control are predicated on apriori knowledge of disturbances a system might face. This paper proposes a method to efficiently learn these disturbances in a risk-aware online context.
  arXiv  Detail & Related papers  (2022-12-12T21:40:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.