← Back to all news
arXiv Machine Learning By Samantha Chen, Jesse He, Coleman Clougherty, Gal Mishne, Chester Holtz

Neural Algorithmic Reasoning for Graph Saddle Point Problems

Read the original on arXiv Machine Learning →

The paper introduces “GraphPDHG,” a message‑passing neural network that aligns with the Chambolle‑Pock Primal–Dual Hybrid Gradient algorithm to solve general graph saddle‑point problems. The authors prove that “GraphPDHG” can efficiently simulate PDHG and can learn an accelerated version of the algorithm. Experiments demonstrate that the learned warm start improves second‑order optimizers and that alignment with PDHG yields better size generalization compared to standard GNN baselines.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 25

Which Algorithms Can Graph Neural Networks Learn?

arXiv:2602.13106v2 Announce Type: replace-cross Abstract: In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a li...

By Solveig Wittig, Antonis Vasileiou, Robert R. Nerem, Timo Stoll, Floris Geerts, Yusu Wang, Christopher Morris
efficiency
More like this →
arXiv Machine Learning
Jun 2

Learning-Augmented Scalable Linear Assignment Problem Optimization via Neural Dual Warm-Starts

arXiv:2605. 09382v2 Announce Type: replace Abstract: The Linear Assignment Problem is a fundamental combinatorial optimization task where classical exact solvers ensure optimality but suffer from an $\mathcal{O}(N^{3})$ bottleneck, while recent neural approximations struggle with scalability and exactness.

By Ilay Yavlovich, Jad Agbaria, Muhamed Mhamed, Nir Weinberger, Jose Yallouz
More like this →
arXiv AI
Jun 26

Learning to Select Maximum Clique Algorithms: From Traditional Machine Learning to a Dual-Channel Hybrid Neural Architecture

arXiv:2508. 08005v4 Announce Type: replace-cross Abstract: The Maximum Clique Problem (MCP) is an NP-hard problem with wide-ranging applications in fields such as bioinformatics, network science, and social computing, yet no single algorithm consistently outperforms all others across diverse graph instances.

By Xiang Li, Shanshan Wang, Chenglong Xiao
agentsbenchmarks
More like this →
arXiv Machine Learning
Aug 27

SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programming

The paper introduces SHSP, a Structure-Aware Hierarchical Solution Prediction framework for Mixed-Integer Linear Programming. SHSP replaces one-shot marginal decoding with a hierarchical conditional decoding that sequentially predicts variables based on a coupling graph derived from constraints, and includes a confidence-aware mask-and-repair step to correct errors. Experiments on four MILP benchmarks show SHSP reduces the solution gap by an average of 54% compared to existing one-shot methods.

By Zherong Zhang, Guanlin Li, Chengrui Gao, Haopu Shang, Ke Xue, Jixiang Lu, Weiyong Yang, Chao Qian
benchmarks
More like this →