Conditional Value-at-Risk

Also known as CVaR

Overview

Conditional Value-at-Risk (CVaR) captures the average severity of outcomes beyond a chosen loss quantile, helping decisions account for rare but costly events. Methods use threshold-based optimization, risk-sensitive reinforcement learning and control, distributionally robust estimation, and conformal calibration to manage tail risk. Applications include portfolio selection, safe robotics, and planning under uncertainty, with guarantees studied for learning and policy evaluation. A central challenge is that tail estimates depend on few observations, so quantile errors and distribution shifts can make risk-aware decisions unstable even when the estimator is robust.

Latest papers

CardsList

32 papers6 papers in the last four weeks, up 50% on the four weeks before. 0.0% of all new papers.

  1. Quantification of Tail-trimming Effects for Interval CVaR Based Nonlinear Regression

    Jan 16, 2026Yulei You, Junyi LiuRobust RegressionDistribution Shift Robustness

  2. Risk-averse learning with delayed feedback

    Sep 25, 2024Siyi Wang, Zifan Wang, Karl Henrik Johansson +1Dynamic Regret MinimizationZeroth-Order Optimization