Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications

2026-09-04

AI Summary

该论文综述了学习增强算法在处理不可靠预测时保持性能保证的方法，探讨了其构建机制、误差度量及系统层面的影响。

Abstract

Learning-augmented algorithms use fallible predictions while retaining formal performance guarantees. This survey synthesizes prediction interfaces, error measures, consistency--robustness trade-offs, and five representative construction mechanisms across online optimization, caching, learned data structures, graph problems, and mechanism design. An orthogonal theorem-level axis distinguishes achieved upper bounds from matched asymptotic dependence. Formal guarantees are separated from empirical systems evidence, with explicit treatment of prediction cost, feedback, and composition. The resulting synthesis states sufficient conditions for limited end-to-end reasoning and delineates open problems in cost-aware prediction, endogenous error, semantic predictors, and benchmarking.

Problem

• learning-augmented algorithms
• performance guarantees
• prediction errors
• construction mechanisms
• system-level implications

Innovation

• Learning-augmented algorithms
• Performance guarantees
• Prediction interfaces
• Consistency-robustness trade-offs
• Construction mechanisms