Fangzhou Zhu

Latest

• Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental Graph
• Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learning
• Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming
• Differentiable Integer Linear Programming
• Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph
• Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
• Rethinking Branching on Exact Combinatorial OPtimization Solver: The First Deep Symbolic Discovery Framework