Alert button
Picture for Bethany Wang

Bethany Wang

Alert button

Learning to Optimize with Stochastic Dominance Constraints

Nov 21, 2022
Hanjun Dai, Yuan Xue, Niao He, Bethany Wang, Na Li, Dale Schuurmans, Bo Dai

Figure 1 for Learning to Optimize with Stochastic Dominance Constraints
Figure 2 for Learning to Optimize with Stochastic Dominance Constraints
Figure 3 for Learning to Optimize with Stochastic Dominance Constraints
Figure 4 for Learning to Optimize with Stochastic Dominance Constraints

In real-world decision-making, uncertainty is important yet difficult to handle. Stochastic dominance provides a theoretically sound approach for comparing uncertain quantities, but optimization with stochastic dominance constraints is often computationally expensive, which limits practical applicability. In this paper, we develop a simple yet efficient approach for the problem, the Light Stochastic Dominance Solver (light-SD), that leverages useful properties of the Lagrangian. We recast the inner optimization in the Lagrangian as a learning problem for surrogate approximation, which bypasses apparent intractability and leads to tractable updates or even closed-form solutions for gradient calculations. We prove convergence of the algorithm and test it empirically. The proposed light-SD demonstrates superior performance on several representative problems ranging from finance to supply chain management.

* 24 pages, 44 figures 
Viaarxiv icon