Primal-Dual Algorithms with Predictions for Online Bounded Allocation and Ad-Auctions Problems

TL;DR

This paper introduces primal-dual algorithms that leverage machine learning predictions to improve online matching and ad-auction problems, achieving better performance with accurate predictions while maintaining worst-case guarantees.

Contribution

It develops prediction-augmented primal-dual algorithms for online allocation and ad-auctions, bridging machine learning and classical optimization for improved solutions.

Findings

Algorithms outperform classical bounds with accurate predictions.

Performance degrades gracefully with inaccurate predictions.

Experimental results support theoretical claims.

Abstract

Matching problems have been widely studied in the research community, especially Ad-Auctions with many applications ranging from network design to advertising. Following the various advancements in machine learning, one natural question is whether classical algorithms can benefit from machine learning and obtain better-quality solutions. Even a small percentage of performance improvement in matching problems could result in significant gains for the studied use cases. For example, the network throughput or the revenue of Ad-Auctions can increase remarkably. This paper presents algorithms with machine learning predictions for the Online Bounded Allocation and the Online Ad-Auctions problems. We constructed primal-dual algorithms that achieve competitive performance depending on the quality of the predictions. When the predictions are accurate, the algorithms' performance surpasses previous performance bounds, while when the predictions are misleading, the algorithms maintain standard worst-case performance guarantees. We provide supporting experiments on generated data for our theoretical findings.