Online Algorithms with Unreliable Guidance

2026-02-24

AI Summary

This work addresses the challenge of machine learning predictions being subject to adversarial corruption by introducing the “Online Algorithms with Unreliable Advice” (OAG) model, which decouples prediction from algorithmic decision-making. Within a request-response game framework, the model captures scenarios where advice is maliciously corrupted with probability β. The key contribution is the design of the DTB (Drop or Trust Blindly) compiler, which achieves an optimal theoretical trade-off between consistency and robustness using only two simple strategies: blindly trusting or outright discarding the advice. This approach attains the best-known performance in caching and uniform metrical task systems and outperforms existing state-of-the-art algorithms for online bipartite matching under adversarial arrival orders.

Technology Category

• Machine Learning: Online Learning & Bandits
• Multiagent Systems: Adversarial Agents
• Search and Optimization: Adversarial Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

This paper introduces a new model for ML-augmented online decision making, called online algorithms with unreliable guidance (OAG). This model completely separates between the predictive and algorithmic components, thus offering a single well-defined analysis framework that relies solely on the considered problem. Formulated through the lens of request-answer games, an OAG algorithm receives, with each incoming request, a piece of guidance which is taken from the problem's answer space; ideally, this guidance is the optimal answer for the current request, however with probability $\beta$, the guidance is adversarially corrupted. The goal is to develop OAG algorithms that admit good competitiveness when $\beta = 0$ (a.k.a. consistency) as well as when $\beta = 1$ (a.k.a. robustness); the appealing notion of smoothness, that in most prior work required a dedicated loss function, now arises naturally as $\beta$ shifts from $0$ to $1$. We then describe a systematic method, called the drop or trust blindly (DTB) compiler, which transforms any online algorithm into a learning-augmented online algorithm in the OAG model. Given a prediction-oblivious online algorithm, its learning-augmented counterpart produced by applying the DTB compiler either follows the incoming guidance blindly or ignores it altogether and proceeds as the initial algorithm would have; the choice between these two alternatives is based on the outcome of a (biased) coin toss. As our main technical contribution, we prove (rigorously) that although remarkably simple, the class of algorithms produced via the DTB compiler includes algorithms with attractive consistency-robustness guarantees for three classic online problems: for caching and uniform metrical task systems our algorithms are optimal, whereas for bipartite matching (with adversarial arrival order), our algorithm outperforms the state-of-the-art.

Problem

• online algorithms
• unreliable guidance
• learning-augmented algorithms
• consistency
• robustness

Innovation

• online algorithms
• learning-augmented algorithms
• unreliable guidance
• consistency-robustness tradeoff
• DTB compiler