5 papers
Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling
Jialin Liu, Lisang Ding, Stanley Osher +1
Implicit models, an emerging model class, compute outputs by iterating a single parameter block to a fixed point. This architecture realizes an infinite-depth, weight-tied network…
Automating Reformulation for Parallel ADMM
Kaizhao Sun, Baihao Wu, Kun Yuan +1
Many real-world optimization models contain exploitable sparsity and block structure, but this structure is often obscured in algebraic form, limiting the effectiveness of modern p…
Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery
HanQin Cai, Chandra Kundu, Jialin Liu +1
Robust matrix completion (RMC) is a widely used machine learning tool that simultaneously tackles two critical issues in low-rank data analysis: missing data entries and extreme ou…
Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs
Ziang Chen, Xiaohan Chen, Jialin Liu +2
Quadratic programming (QP) is the most widely applied category of problems in nonlinear programming. Many applications require real-time/fast solutions, though not necessarily with…
Rethinking the Capacity of Graph Neural Networks for Branching Strategy
Ziang Chen, Jialin Liu, Xiaohan Chen +2
Graph neural networks (GNNs) have been widely used to predict properties and heuristics of mixed-integer linear programs (MILPs) and hence accelerate MILP solvers. This paper inves…