More Like this

1. Stochastic Optimization Forests

   https://doi.org/10.1287/mnsc.2022.4458  

   Kallus, Nathan; Mao, Xiaojie (January 2022, Management Science)

   We study contextual stochastic optimization problems, where we leverage rich auxiliary observations (e.g., product characteristics) to improve decision making with uncertain variables (e.g., demand). We show how to train forest decision policies for this problem by growing trees that choose splits to directly optimize the downstream decision quality rather than split to improve prediction accuracy as in the standard random forest algorithm. We realize this seemingly computationally intractable problem by developing approximate splitting criteria that use optimization perturbation analysis to eschew burdensome reoptimization for every candidate split, so that our method scales to large-scale problems. We prove that our splitting criteria consistently approximate the true risk and that our method achieves asymptotic optimality. We extensively validate our method empirically, demonstrating the value of optimization-aware construction of forests and the success of our efficient approximations. We show that our approximate splitting criteria can reduce running time hundredfold while achieving performance close to forest algorithms that exactly reoptimize for every candidate split. This paper was accepted by Hamid Nazerzadeh, data science. 

   more » « less
2. Accelerating Stochastic Composition Optimization

   Mengdi Wang, Ji Liu (January 2017, Journal of machine learning research)
3. Federated Conditional Stochastic Optimization

   Wu, Xidong; Sun, Jianhui; Hu, Zhengmian; Li, Junyi; Zhang, Aidong; Huang, Heng (December 2023, Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023))
4. Deep stochastic optimization in finance

   https://doi.org/10.1007/s42521-022-00074-6  

   Reppen, A Max; Soner, H Mete; Tissot-Daguette, Valentin (March 2023, Digital Finance)

   This paper outlines, and through stylized examples evaluates a novel and highly effective computational technique in quantitative finance. Empirical Risk Minimi- zation (ERM) and neural networks are key to this approach. Powerful open source optimization libraries allow for efficient implementations of this algorithm making it viable in high-dimensional structures. The free-boundary problems related to Amer- ican and Bermudan options showcase both the power and the potential difficulties that specific applications may face. The impact of the size of the training data is studied in a simplified Merton type problem. The classical option hedging problem exemplifies the need of market generators or large number of simulations. 

   more » « less
5. Data Pooling in Stochastic Optimization

   https://doi.org/10.1287/mnsc.2020.3933  

   Gupta, Vishal; Kallus, Nathan (January 2021, Management Science)

   null (Ed.)

   Managing large-scale systems often involves simultaneously solving thousands of unrelated stochastic optimization problems, each with limited data. Intuition suggests that one can decouple these unrelated problems and solve them separately without loss of generality. We propose a novel data-pooling algorithm called Shrunken-SAA that disproves this intuition. In particular, we prove that combining data across problems can outperform decoupling, even when there is no a priori structure linking the problems and data are drawn independently. Our approach does not require strong distributional assumptions and applies to constrained, possibly nonconvex, nonsmooth optimization problems such as vehicle-routing, economic lot-sizing, or facility location. We compare and contrast our results to a similar phenomenon in statistics (Stein’s phenomenon), highlighting unique features that arise in the optimization setting that are not present in estimation. We further prove that, as the number of problems grows large, Shrunken-SAA learns if pooling can improve upon decoupling and the optimal amount to pool, even if the average amount of data per problem is fixed and bounded. Importantly, we highlight a simple intuition based on stability that highlights when and why data pooling offers a benefit, elucidating this perhaps surprising phenomenon. This intuition further suggests that data pooling offers the most benefits when there are many problems, each of which has a small amount of relevant data. Finally, we demonstrate the practical benefits of data pooling using real data from a chain of retail drug stores in the context of inventory management. This paper was accepted by Chung Piaw Teo, Special Issue on Data-Driven Prescriptive Analytics. 

   more » « less