Learning-augmented algorithms combine fallible predictions with formal performance guarantees. This survey reviews prediction interfaces, error measures, consistency–robustness trade-offs, and five construction mechanisms across online optimization, caching, learned data structures, graph problems, and mechanism design. It distinguishes theorem-level upper bounds from matched asymptotic dependence, separates formal guarantees from empirical evidence, and outlines open problems in cost-aware prediction, endogenous error, semantic predictors, and benchmarking.
By Hailiang Zhao, Peng Chen, Xueyan Tang, Jianwei Yin, Shuiguang Deng
arXiv:2606. 05380v1 Announce Type: cross Abstract: We present learning-augmented algorithms for two general classes of online minimization problems: metrical task systems and laminar set cover.
By Christian Coester, Alexa Tudose, Alexander Turoczy
arXiv:2506. 20573v4 Announce Type: replace-cross Abstract: Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can harm model performance.
By Kristian Minchev, Dimitar I. Dimitrov, Nikola Konstantinov
arXiv:2607. 27807v1 Announce Type: new Abstract: This paper studies learning-augmented and randomized online aggregation with delays on a line metric.
By Tianhang Lu, Runtian Ren, Shengcai Liu, Ke Tang
arXiv:2608. 13554v1 Announce Type: new Abstract: We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary.
By Georgy Noarov, Aaron Roth
The paper presents a unified framework for regularization-based robust reinforcement learning by deriving upper bounds on the performance gap between nominal and worst-case policies. These bounds are expressed as a regularization objective plus a KL-divergence penalty, explaining why KL penalties enhance robustness. The authors reformulate robust training as a constrained optimization problem, updating the Lagrange multiplier jointly with the policy to automatically tune regularization, and validate the approach with extensive adversarial evaluations on continuous control tasks.
By Amine Andam, Jamal Bentahar, Mustapha Hedabou
arXiv:2602. 01903v2 Announce Type: replace Abstract: This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds algorithms that achieve refined data-dependent regret bounds in the adversarial regime and variance-dependent regret bounds in the stochastic regime.
By Mingyi Li, Taira Tsuchiya, Kenji Yamanishi
The paper addresses the challenge of creating machine learning learners that can guarantee provably correct predictions in difficult test-time scenarios, such as adversarial attacks and natural distribution shifts. It introduces a reliable learner with optimal theoretical guarantees for these settings and discusses practical implementations. The authors demonstrate strong performance on examples like linear separators under log-concave distributions and smooth boundary classifiers under smooth probability distributions.
By Maria-Florina Balcan, Steve Hanneke, Rattana Pukdee, Dravyansh Sharma
arXiv:2608. 13514v1 Announce Type: cross Abstract: We revisit the problem of learning predictors robust to adversarial examples at test-time.
By Omar Montasser
arXiv:2606. 22831v2 Announce Type: replace-cross Abstract: This paper studies learning-augmented online weighted vertex cover with local advice and a tradeoff parameter $\lambda \in (0,1)$.
By Tianhang Lu, Runtian Ren, Shengcai Liu
arXiv:2607. 20822v1 Announce Type: new Abstract: Motivated by reinforcement learning in harsh environments, we consider the problem of learning an optimal policy subject to adversarially corrupted feedback.
By Sreejeet Maity, Aritra Mitra
arXiv:2605. 29032v2 Announce Type: replace Abstract: Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss.
By Christoph Dann, Yishay Mansour, Mehryar Mohri