Research map / Learning theory and algorithms / Combinatorial and search optimization

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

ICLR 2025 · Learning theory and algorithms › Combinatorial and search optimization · approach: Unsupervised neural combinatorial optimization

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Unifies machine-learning solvers for the Travelling Salesman Problem into a streamlined design space of learning and search, and introduces ML4TSPBench as a modular benchmark framework.

Problem

A unified, principled framework for machine learning on combinatorial optimization is lacking, with TSP used as the main case study.

Approach

Dissects established mainstream learning-based TSP solvers to outline a comprehensive design space of learning and search components, and packages it as a unified modular benchmark (ML4TSPBench) that is said to extend to other CO problems.

Closest papers by meaning

• Learning to Solve Travelling Salesman Problem with Hardness-Adaptive Curriculum (AAAI 2022 · similarity 0.91)
• Position: Rethinking Post-Hoc Search-Based Neural Approaches for Solving Large-Scale Traveling Salesman Problems (ICML 2024 · similarity 0.90)
• Beyond the Heatmap: A Rigorous Evaluation of Component Impact in MCTS-Based TSP Solvers (ICLR 2026 · similarity 0.90)
• FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization (ICLR 2026 · similarity 0.89)
• Neural Solver Selection for Combinatorial Optimization (ICML 2025 · similarity 0.89)
• DualOpt: A Dual Divide-and-Optimize Algorithm for the Large-scale Traveling Salesman Problem (AAAI 2025 · similarity 0.88)