Learning to Optimize Contextually Constrained Problems for Real-Time Decision-Generation
This addresses real-time decision-making challenges in operations research and machine learning applications, though it appears to be an incremental/hybrid approach combining existing techniques.
The authors tackled the problem of generating optimal decisions for continuous optimization problems with context-dependent constraints by developing a framework combining interior point methods and adversarial learning. Their approach achieved in-sample and out-of-sample optimality guarantees and outperformed predict-then-optimize and supervised deep learning methods in portfolio optimization and personalized treatment design case studies.
The topic of learning to solve optimization problems has received interest from both the operations research and machine learning communities. In this work, we combine techniques from both fields to address the problem of learning to generate decisions to instances of continuous optimization problems where the feasible set varies with contextual features. We propose a novel framework for training a generative model to estimate optimal decisions by combining interior point methods and adversarial learning, which we further embed within an data generation algorithm. Decisions generated by our model satisfy in-sample and out-of-sample optimality guarantees. Finally, we investigate case studies in portfolio optimization and personalized treatment design, demonstrating that our approach yields advantages over predict-then-optimize and supervised deep learning techniques, respectively.