Research map / Learning theory and algorithms / Combinatorial and search optimization

Decision Focused Scenario Learning for Contextual Stochastic Programming

NeurIPS 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Decision-focused optimization

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies decision-focused scenario generation for contextual two-stage stochastic programming, addressing when generators yield optimal policies and handling non-differentiability of decision-focused losses.

Problem

Contextual two-stage stochastic programming needs scenario generators whose outputs yield optimal decisions; existing decision-focused scenario learning lacks a general theory and often assumes strict restrictions on which second-stage data may be random, and the decision-focused objective is non-di

Approach

Provides a general theory for when scenario generators can produce optimal decision policies and relaxes assumptions on which second-stage data may be random; details beyond the abstract are not stated.

Closest papers by meaning

• HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming (ICML 2024 · similarity 0.87)
• Contextual Optimization Under Model Misspecification: A Tractable and Generalizable Approach (ICML 2025 · similarity 0.86)
• Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints (NeurIPS 2025 · similarity 0.86)
• Selective Uncertainty Propagation in Offline RL (AAAI 2025 · similarity 0.85)
• Cost-Aware Near-Optimal Policy Learning (AAAI 2025 · similarity 0.85)
• Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty (NeurIPS 2026 · similarity 0.85)