Affine estimators minimizing worst-case CVaR of squared error over a type-2 Wasserstein ambiguity set can be exactly computed via tractable SDP when the nominal distribution is finitely supported.
Near-optimality of linear recovery in Gaussian observation scheme under∥ · ∥ 2 2-loss,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Risk
Affine estimators minimizing worst-case CVaR of squared error over a type-2 Wasserstein ambiguity set can be exactly computed via tractable SDP when the nominal distribution is finitely supported.