arXiv Machine Learning June 25, 2026 By Sungwoo Kang

Learning Structural Hardness for Combinatorial Auctions: Instance-Dependent Algorithm Selection via Graph Neural Networks

Read the original on arXiv Machine Learning →

arXiv:2602. 14772v2 Announce Type: replace Abstract: The Winner Determination Problem (WDP) in combinatorial auctions is NP-hard, and no existing method reliably predicts which instances will defeat fast greedy heuristics.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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

agents benchmarks

arXiv Machine Learning

Jul 22

Graph Neural Network-based Algorithm Selection for the Traveling Salesman Problem: A Systematic Study of Cost and Rank Losses under Distinct Budget Regimes

arXiv:2607. 18632v1 Announce Type: new Abstract: Automated Algorithm Selection (AS) aims to improve problem-solving performance by selecting, for each problem instance, the most suitable algorithm from a predefined portfolio.

By Zhaoxuan Li, Jiale Yang, Yifei Lu, Mustafa Misir

arXiv Machine Learning

Jun 17

Amortizing Maximum Inner Product Search with Learned Support Functions

arXiv:2603. 08001v2 Announce Type: replace Abstract: Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a given query.

By Theo X. Olausson, Jo\~ao Monteiro, Michal Klein, Marco Cuturi

rag benchmarks

arXiv Machine Learning

Jul 2

Amortized Maximum Inner Product Search with Learned Support Functions

arXiv:2603. 08001v3 Announce Type: replace Abstract: Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a given query.

By Theo X. Olausson, Jo\~ao Monteiro, Michal Klein, Marco Cuturi

rag benchmarks

arXiv AI

Jul 14

Transformer-Guided Swarm Intelligence for Frugal Neural Architecture Search

arXiv:2607. 11826v1 Announce Type: cross Abstract: Neural Architecture Search (NAS) has automated the design of deep learning models but traditionally requires massive computational resources, often measured in thousands of GPU-days.

By Romain Amigon

llms reinforcement-learning efficiency

Hugging Face Trending Papers

Jul 21

Graph Neural Network-based Algorithm Selection for the Traveling Salesman Problem: A Systematic Study of Cost and Rank Losses under Distinct Budget Regimes

Automated Algorithm Selection (AS) aims to improve problem-solving performance by selecting, for each problem instance, the most suitable algorithm from a predefined portfolio. This is particularly relevant to the Traveling Salesman Problem (TSP), where solver performance is strongly instance-dependent.

Related stories

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

Graph Neural Network-based Algorithm Selection for the Traveling Salesman Problem: A Systematic Study of Cost and Rank Losses under Distinct Budget Regimes

Amortizing Maximum Inner Product Search with Learned Support Functions

Amortized Maximum Inner Product Search with Learned Support Functions

Transformer-Guided Swarm Intelligence for Frugal Neural Architecture Search

Graph Neural Network-based Algorithm Selection for the Traveling Salesman Problem: A Systematic Study of Cost and Rank Losses under Distinct Budget Regimes