arrow
Return

Solving two-stage stochastic integer programs via representation learning

delete2025-05-27
delete0
PRE
AI
Y
Yaoxin Wu
Z
Zhiguang Cao
W
Wen Song *
Y
Yingqian Zhang
DOI:10.1016/j.neunet.2025.107446delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
Solving stochastic integer programs (SIPs) is extremely intractable due to the high computational complexity. To solve two-stage SIPs efficiently, we propose a conditional variational autoencoder (CVAE) for scenario representation learning. A graph convolutional network (GCN) based VAE embeds scenarios into a low-dimensional latent space, conditioned on the deterministic context of each instance. With the latent representations of stochastic scenarios, we perform two auxiliary tasks: objective prediction and scenario contrast, which predict scenario objective values and the similarities between them, respectively. These tasks further integrate objective information into the representations through gradient backpropagation. Experiments show that the learned scenario representations can help reduce scenarios in SIPs, facilitating high-quality solutions in a short computational time. This superiority generalizes well to instances of larger sizes, more scenarios, and various distributions.
Keywords:
Stochastic integer programs
Conditional variational autoencoder
Semi-supervised learning
Contrastive learning

Journal

Neural Networks cover
Neural Networks
IF:
6.3
Papers:
8.4K
Citations:
3.9W

Organization

S
singapore management univ singapore
Scholars:
1
Papers: 1
Citations: 2
Cited Papers

Cited Papers

The Benders Dual Decomposition Method
err2020-05-01
err0
PREAI
errRagheb Rahmaniani; Shabbir Ahmed; Teodor Gabriel Crainic; Michel Gendreau; Walter Rei
errShare
errSave
The Sample Average Approximation Method for Stochastic Discrete Optimization
err2002-01-01
err0
errOAAI
errAnton J. Kleywegt; Alexander Shapiro; Tito Homem-de-Mello
errShare
errSave
Problem-driven scenario clustering in stochastic optimization
err2023-03-15
err0
PREAI
errJulien Keutchayan; Janosch Ortmann; Walter Rei
errShare
errSave
A Learning-Based Algorithm to Quickly Compute Good Primal Solutions for Stochastic Integer Programs
err2020-09-19
err0
errOAAI
errYoshua Bengio; Emma Frejinger; Andrea Lodi; Rahul Patel; Sriram Sankaranarayanan
errShare
errSave
Predicting Tactical Solutions to Operational Planning Problems Under Imperfect Information
err2022-01-01
err0
errOAAI
errEric Larsen; Sébastien Lachapelle; Yoshua Bengio; Emma Frejinger; Simon Lacoste-Julien; Andrea Lodi
errShare
errSave
errShare
errSave
A review on learning to solve combinatorial optimisation problems in manufacturing
err2023-03-03
err0
errOAAI
errCong Zhang; Yaoxin Wu; Yining Ma; Wen Song; Zhang Le; Zhiguang Cao; Jie Zhang
errShare
errSave
errShare
errSave
researcher View more