Skip to content

Wasserstein Distributionally Robust Risk-Sensitive Estimation

Home / Concepts / Wasserstein Distributionally Robust Risk-Sensitive Estimation

Wasserstein Distributionally Robust Risk-Sensitive Estimation

Auto-generated stub. Edit this file to add more details.

An estimation framework that minimizes the worst-case conditional value-at-risk of the squared error within a type-2 Wasserstein ambiguity set.

Why It Matters

Provides a rigorous framework for uncertainty quantification in time-series forecasting by optimizing worst-case performance under Wasserstein distribution ambiguity.

Evidence

We propose a distributionally robust approach to risk-sensitive estimation of an unknown signal x from an observed signal y… The performance of an estimator is measured according to the conditional value-at-risk (CVaR) of the squared estimation error.

Metadata & Links