REVIEW 7 cited by
Distributionally Robust Optimization: A Review
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The concepts of risk-aversion, chance-constrained optimization, and robust optimization have developed significantly over the last decade. Statistical learning community has also witnessed a rapid theoretical and applied growth by relying on these concepts. A modeling framework, called distributionally robust optimization (DRO), has recently received significant attention in both the operations research and statistical learning communities. This paper surveys main concepts and contributions to DRO, and its relationships with robust optimization, risk-aversion, chance-constrained optimization, and function regularization.
Forward citations
Cited by 7 Pith papers
-
Distributionally Robust Shape and Topology Optimization
The paper derives tractable single-level reformulations of distributionally robust shape and topology optimization for Wasserstein, moment, and CVaR ambiguity sets, and demonstrates them numerically.
-
A New Perspective On AI Safety Through Control Theory Methodologies
This paper outlines a new conceptual paradigm, data control, which transfers control-theoretic system analysis and properties to AI systems to support generic AI safety assurance.
-
Multi-Agent Inverse Reinforcement Learning for Identifying Pareto-Efficient Coordination -- A Distributionally Robust Approach
Multi-agent coordination is detected by a feasibility LP, converted to a Type-I-error-controlled detector, and agent utilities are reconstructed with a Wasserstein distributionally robust estimator.
-
Harmonizing SAA and DRO
Weighted SAA and moment-DRO with lambda = C/sqrt(N) combines data and information, is asymptotically optimal at a 1/sqrt(N) rate, and improves scenario reduction.
-
Distributionally Robust Deep Q-Learning
Sinkhorn-ball robust Bellman equation for continuous-state MDPs is implemented as a Robust DQN that learns policies robust to transition-model misspecification.
-
Calibrating Decision Robustness via Inverse Conformal Risk Control
A conformal-style estimator certifies simultaneous upper bounds on miscoverage and regret for robust predict-then-optimize policies, tracing a Pareto frontier for choosing the robustness level.
-
Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates
The paper derives a 'Divergence Theory' of negative off-policy updates and proposes hard-filtering (DRPO), but the key proof is invalid and the method largely re-implements known top-K/CVaR ideas.
Discussion (0). Continue with ORCID to comment.