papers

Publications (15)

math.OC2026

From Sequential to Parallel: Reformulating Dynamic Programming as GPU Kernels for Large-Scale Stochastic Combinatorial Optimization

Jingyi Zhao, Linxin Yang, Haohua Zhang +2

A major bottleneck in scenario-based Sample Average Approximation (SAA) for stochastic programming (SP) is the cost of solving an exact second-stage problem for every scenario, esp…

cs.LG2022

The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights

Maxime Gasse, Quentin Cappart, Jonas Charfreitag +38

Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolatio…

math.OC2025

A Learning-Based Inexact ADMM for Solving Quadratic Programs

Xi Gao, Jinxin Xiong, Linxin Yang +3

Convex quadratic programs (QPs) constitute a fundamental computational primitive across diverse domains including financial optimization, control systems, and machine learning. The…

math.OC2022

Efficient primal heuristics for mixed-integer linear programs

Akang Wang, Linxin Yang, Sha Lai +7

This paper is a short report about our work for the primal task in the Machine Learning for Combinatorial Optimization NeurIPS 2021 Competition. For each dataset of our interest in…

math.OC2025

Solving Quadratic Programs via Deep Unrolled Douglas-Rachford Splitting

Jinxin Xiong, Xi Gao, Linxin Yang +3

Convex quadratic programs (QPs) are fundamental to numerous applications, including finance, engineering, and energy systems. Among the various methods for solving them, the Dougla…

math.OC2025

GPU-based Split algorithm for Large-Scale CVRPSD

Jingyi Zhao, Linxin Yang, Haohua Zhang +1

Dynamic programming (DP) is a cornerstone of combinatorial optimization, yet its inherently sequential structure has long limited its scalability in scenario-based stochastic progr…

math.OC2023

A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming

Qingyu Han, Linxin Yang, Qian Chen +5

Mixed-integer linear programming (MILP) is widely employed for modeling combinatorial optimization problems. In practice, similar MILP instances with only coefficient variations ar…

cs.CL2026

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

Dongfang Li, Xiaodong Luo, Ruoyu Sun +64

Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pre…

cs.LG2025

QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks

Qian Chen, Linxin Yang, Akang Wang +2

The combination of linear transformations and non-linear activation functions forms the foundation of most modern deep neural networks, enabling them to approximate highly complex…

math.OC2025

SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization

Qian Chen, Tianjian Zhang, Linxin Yang +5

Integer linear programs (ILPs) are commonly employed to model diverse practical problems such as scheduling and planning. Recently, machine learning techniques have been utilized t…

cs.LG2026

Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices

Qingyu Han, Qian Li, Linxin Yang +3

Integer Linear Programs (ILPs) are central to real-world optimizations but notoriously difficult to solve. Learning to Optimize (L2O) has emerged as a promising paradigm, with Grap…

math.OC2025

Successive Fixing for Large-Scale SCUC Using First-Order Methods

Jinxin Xiong, Yanting Huang, Yingxiao Wang +4

Security-Constrained Unit Commitment is a fundamental optimization problem in power systems operations. The primary computational bottleneck arises from the need to solve large-sca…

math.OC2025

Relax-and-Cut for Temporal SCUC Decomposition

Jinxin Xiong, Linxin Yang, Yingxiao Wang +4

The Security-Constrained Unit Commitment (SCUC) problem presents formidable computational challenges due to its combinatorial complexity, large-scale network dimensions, and numero…

cs.LG2024

PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming

Bingheng Li, Linxin Yang, Yupeng Chen +8

Solving large-scale linear programming (LP) problems is an important task in various areas such as communication networks, power systems, finance and logistics. Recently, two disti…

math.OC2024

An Efficient Unsupervised Framework for Convex Quadratic Programs via Deep Unrolling

Linxin Yang, Bingheng Li, Tian Ding +6

Quadratic programs (QPs) arise in various domains such as machine learning, finance, and control. Recently, learning-enhanced primal-dual hybrid gradient (PDHG) methods have shown…