12 papers
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
Dongfang Li, Xiaodong Luo, Ruoyu Sun +62
Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pre…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
Learning to optimize by multi-gradient for multi-objective optimization
Linxi Yang, Xinmin Yang, Liping Tang
The development of artificial intelligence (AI) for science has led to the emergence of learning-based research paradigms, necessitating a compelling reevaluation of the design of…