Pith. sign in

Optimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We consider optimal transport based distributionally robust optimization (DRO) problems with locally strongly convex transport cost functions and affine decision rules. Under conventional convexity assumptions on the underlying loss function, we obtain structural results about the value function, the optimal policy, and the worst-case optimal transport adversarial model. These results expose a rich structure embedded in the DRO problem (e.g. strong convexity even if the non-DRO problem was not strongly convex, a suitable scaling of the Lagrangian for the DRO constraint, etc. which are crucial for the design of efficient algorithms). As a consequence of these results, one can develop efficient optimization procedures which have the same sample and iteration complexity as a natural non-DRO benchmark algorithm such as stochastic gradient descent.

fields

math.OC 1

years

2019 1

verdicts

UNVERDICTED 1

representative citing papers

Distributionally Robust Optimization: A Review

math.OC · 2019-08-13 · unverdicted · novelty 0.0

A broad review of distributionally robust optimization that organizes the literature by ambiguity-set type and connects DRO to robust optimization, risk aversion, chance constraints, and regularization.

citing papers explorer

Showing 1 of 1 citing paper.

  • Distributionally Robust Optimization: A Review math.OC · 2019-08-13 · unverdicted · none · ref 53 · internal anchor

    A broad review of distributionally robust optimization that organizes the literature by ambiguity-set type and connects DRO to robust optimization, risk aversion, chance constraints, and regularization.