Introduces structured DRO for learned inverse problem reconstructions with ambiguity sets aligned to the forward operator, yielding explicit dual representations and a worst-case bound that induces Tikhonov regularization on the operator Lipschitz constant.
Unifying distribution- ally robust optimization via optimal transport theory
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DR-MOO adds distributional robustness to multi-objective optimization and gives single-loop MGDA algorithms reaching epsilon-Pareto-stationary points in O(epsilon^{-4}) samples for nonconvex problems.
Sinkhorn divergence defines ambiguity sets that make distributionally robust linear quadratic control over linear policies solvable via convex programming even with safety constraints.
citing papers explorer
-
A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems
Introduces structured DRO for learned inverse problem reconstructions with ambiguity sets aligned to the forward operator, yielding explicit dual representations and a worst-case bound that induces Tikhonov regularization on the operator Lipschitz constant.
-
Distributionally Robust Multi-Objective Optimization
DR-MOO adds distributional robustness to multi-objective optimization and gives single-loop MGDA algorithms reaching epsilon-Pareto-stationary points in O(epsilon^{-4}) samples for nonconvex problems.
-
Sinkhorn Ambiguity Sets for Distributionally Robust Control: Convexity, Weak Compactness, and Tractability
Sinkhorn divergence defines ambiguity sets that make distributionally robust linear quadratic control over linear policies solvable via convex programming even with safety constraints.