AI RESEARCH
Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference
arXiv CS.LG
•
ArXi:2606.00320v1 Announce Type: new 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.