Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty

• URL: http://arxiv.org/abs/2605.14494v1
• Date: Thu, 14 May 2026 07:34:13 GMT
• Title: Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty
• Abstract summary: We introduce PRISE, a problem-driven sequential lookahead that constructs reduced scenario sets by evaluating the marginal impact of each scenario.<n>While PRISE yields high-quality scenario subsets, each selection step requires solving multiple subproblems, making it computationally expensive at scale.<n>We propose NeurPRISE, a neural surrogate model built on a GNN-Transformer backbone that encodes the per-scenario structure via graph convolution.
• Score: 48.1205762141586
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Two-Stage Robust Optimization (2RO) with discrete uncertainty is challenging, often rendering exact solutions prohibitive. Scenario reduction alleviates this issue by selecting a small, representative subset of scenarios to enable tractable computation. However, existing methods are largely problem-agnostic, operating solely on the uncertainty set without consulting the feasible region or recourse structure. In this paper, we introduce PRISE, a problem-driven sequential lookahead heuristic that constructs reduced scenario sets by evaluating the marginal impact of each scenario. While PRISE yields high-quality scenario subsets, each selection step requires solving multiple subproblems, making it computationally expensive at scale. To address this, we propose NeurPRISE, a neural surrogate model built on a GNN-Transformer backbone that encodes the per-scenario structure via graph convolution and captures cross-scenario interactions through attention. NeurPRISE is trained via imitation learning with a gain-aware ranking objective, which distills marginal gain information from PRISE into a learned scoring function for scenario ranking and selection. Extensive results on three 2RO problems show that NeurPRISE consistently achieves competitive regret relative to comprehensive methods, maintains strong calability with varying numbers of scenarios, and delivers 7-200x speedup over PRISE. NeurPRISE also exhibits strong zero-shot generalization, effectively handling instances with larger problem scales (up to 5x), more scenarios (up to 4x), and distribution shifts.

Related papers

• Neural Two-Stage Stochastic Optimization for Solving Unit Commitment Problem [0.8848340429852071]
  This paper proposes a neural optimization method for efficiently solving the two-stage unit commitment (2S-SUC) problem under high-dimensional uncertainty scenarios.<n>The proposed method approximates the second-stage recourse problem using a deep neural network trained to map commitment decisions and uncertainty features to recourse costs.
  arXiv  Detail & Related papers  (2025-07-13T05:55:25Z)
• Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory [10.535721818998649]
  We study the role of randomization in enhancing robustness to adversarial attacks in multiclass classification.<n>We find that switching from a deterministic to a randomized solution significantly reduces the optimal adversarial risk.<n>These findings highlight the crucial role randomization can play in enhancing robustness to adversarial attacks in multiclass classification.
  arXiv  Detail & Related papers  (2025-03-18T14:41:33Z)
• Contextual Scenario Generation for Two-Stage Stochastic Programming [0.2812395851874055]
  Two-stage programs (2SPs) are important tools for making decisions under uncertainty.<n>Current scenario generation approaches do not leverage contextual information or do not address computational concerns.<n>We propose a distributional approach that learns the mapping by minimizing a distributional distance between the predicted surrogate scenarios and the true contextual distribution.<n>Second, we propose a task-based approach that aims to produce surrogate scenarios that yield high-quality decisions.
  arXiv  Detail & Related papers  (2025-02-07T21:42:50Z)
• DSFNet: Learning Disentangled Scenario Factorization for Multi-Scenario Route Ranking [19.448901545665212]
  Multi-scenario route ranking (MSRR) is crucial in many industrial mapping systems. We propose a novel method, Disentangled Scenario Factorization Network (DSFNet), which flexibly composes scenario-dependent parameters. We also propose MSDR, the first large-scale publicly available annotated industrial Multi-Scenario Driving Route dataset.
  arXiv  Detail & Related papers  (2024-03-30T04:39:18Z)
• Large-scale Fully-Unsupervised Re-Identification [78.47108158030213]
  We propose two strategies to learn from large-scale unlabeled data. The first strategy performs a local neighborhood sampling to reduce the dataset size in each without violating neighborhood relationships. A second strategy leverages a novel Re-Ranking technique, which has a lower time upper bound complexity and reduces the memory complexity from O(n2) to O(kn) with k n.
  arXiv  Detail & Related papers  (2023-07-26T16:19:19Z)
• Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization [61.39201891894024]
  Group distributionally robust optimization (group DRO) can minimize the worst-case loss over pre-defined groups. We reformulate the group DRO framework by proposing Q-Diversity. Characterized by an interactive training mode, Q-Diversity relaxes the group identification from annotation into direct parameterization.
  arXiv  Detail & Related papers  (2023-05-20T07:02:27Z)
• RoMA: Robust Model Adaptation for Offline Model-based Optimization [115.02677045518692]
  We consider the problem of searching an input maximizing a black-box objective function given a static dataset of input-output queries. A popular approach to solving this problem is maintaining a proxy model that approximates the true objective function. Here, the main challenge is how to avoid adversarially optimized inputs during the search.
  arXiv  Detail & Related papers  (2021-10-27T05:37:12Z)
• Modeling the Second Player in Distributionally Robust Optimization [90.25995710696425]
  We argue for the use of neural generative models to characterize the worst-case distribution. This approach poses a number of implementation and optimization challenges. We find that the proposed approach yields models that are more robust than comparable baselines.
  arXiv  Detail & Related papers  (2021-03-18T14:26:26Z)
• Combining Deep Learning and Optimization for Security-Constrained Optimal Power Flow [94.24763814458686]
  Security-constrained optimal power flow (SCOPF) is fundamental in power systems. Modeling of APR within the SCOPF problem results in complex large-scale mixed-integer programs. This paper proposes a novel approach that combines deep learning and robust optimization techniques.
  arXiv  Detail & Related papers  (2020-07-14T12:38:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.