演讲人: 葛冬冬 教授，上海交通大学

时间: 2026年6月18日18：30

地点: 同济大厦A楼308教室

讲座摘要:

Mathematical programming is a fundamental engine for intelligent decision-making in complex industrial systems. This talk presents our recent progress on XPU(CPU/GPU/QPU…)-accelerated optimization solvers for large-scale linear, conic, quadratic, and semidefinite programming. By redesigning algorithms, sparse linear algebra, and numerical refinement around modern XPU architectures, we aim to achieve both massive computational speedups and solver-level reliability. I will discuss key algorithmic ideas, hardware–software co-design principles, and applications in power-grid dispatch, EDA, quantum information, robotics, and industrial planning. The talk highlights XPU-accelerated mathematical programming as a critical bridge between high-performance computing and trustworthy AI-driven decision systems.

演讲人简介：

Ge Dongdong is a professor at the Antai College of Economics and Management of Shanghai Jiao Tong University and the dean of the Institute for Intelligent Computing(SJTU-IIC). I obtained my PhD from the Department of Management Science and Engineering at Stanford University in 2009. My main research interests are in the theory, computation, and application of large-scale optimization problems. I publish papers in journals and conferences across multiple fields such as MS/OR/TCS/AI, including OR, MOR, MP, POM, FOCS, SODA, EC, ICML, NeurIPS, etc..I’m also a co-founder and chief scientist of Cardinal Operations(shanshu.ai) and has participated in numerous optimization projects with companies and organizations worldwide, such as Boeing, Google, Huawei, JD.com, SF Express, DiDi, State Grid Corporation of China/Southern Power Grid, and China Southern Airlines. Currently, I serve as the project leader for China’s first open-source mathematical programming software LEAVES and the first commerial mathematical programming software COPT project.