Learning-Augmented Online Minimization with Dual Predictions

• URL: http://arxiv.org/abs/2606.05380v1
• Date: Wed, 03 Jun 2026 19:29:31 GMT
• Title: Learning-Augmented Online Minimization with Dual Predictions
• Abstract summary: We present learning-augmented algorithms for two general classes of online problems: metrical task systems and laminar set cover.<n>Both algorithms achieve improved theoretical guarantees using machine-learned predictions of an optimal solution to the dual linear program.
• Score: 46.123625291724345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present learning-augmented algorithms for two general classes of online minimization problems: metrical task systems and laminar set cover. Both algorithms achieve improved theoretical guarantees using machine-learned predictions of an optimal solution to the dual linear program. Unlike optimal primal solutions, which can change drastically under tiny instance perturbations, these dual solutions are much more stable, which ensures the existence of good (and learnable) predictions for families of similar instances. While previous work has used dual predictions in offline settings and for online maximization problems, our algorithms are, to the best of our knowledge, the first demonstration that such dual predictions can be effective for online minimization. Our theoretical results are complemented by experiments on the $k$-server problem and the parking permit problem.

Related papers

• A Simple Learning-Augmented Algorithm for Online Packing with Concave Objectives [4.9826534303287335]
  We introduce and analyze a simple learning-augmented algorithm for online packing problems with linear constraints and concave objectives. We further raise the problem of understanding necessary and sufficient conditions for when such simple black-box solutions may be optimal.
  arXiv  Detail & Related papers  (2024-06-05T18:39:28Z)
• Near-Optimal Solutions of Constrained Learning Problems [85.48853063302764]
  In machine learning systems, the need to curtail their behavior has become increasingly apparent. This is evidenced by recent advancements towards developing models that satisfy dual robustness variables. Our results show that rich parametrizations effectively mitigate non-dimensional, finite learning problems.
  arXiv  Detail & Related papers  (2024-03-18T14:55:45Z)
• Learning Constrained Optimization with Deep Augmented Lagrangian Methods [54.22290715244502]
  A machine learning (ML) model is trained to emulate a constrained optimization solver. This paper proposes an alternative approach, in which the ML model is trained to predict dual solution estimates directly. It enables an end-to-end training scheme is which the dual objective is as a loss function, and solution estimates toward primal feasibility, emulating a Dual Ascent method.
  arXiv  Detail & Related papers  (2024-03-06T04:43:22Z)
• Dual Interior Point Optimization Learning [16.02181642119643]
  This paper studies how to learn dual feasible solutions that complement primal approaches and provide quality guarantees.<n>The proposed dual completion outperforms methods for learning optimization proxies which do not exploit the structure of the dual problem.
  arXiv  Detail & Related papers  (2024-02-04T20:06:20Z)
• Efficient Methods for Non-stationary Online Learning [63.268670895111654]
  We present efficient methods for optimizing dynamic regret and adaptive regret.<n>The proposed algorithms require only one gradient query and one function evaluation at each round.<n>We also study an even stronger measure, namely "interval dynamic regret", and reduce the number of projections per round from $O(log2 T)$ to $1$.
  arXiv  Detail & Related papers  (2023-09-16T07:30:12Z)
• Online Learning under Budget and ROI Constraints via Weak Adaptivity [57.097119428915796]
  Existing primal-dual algorithms for constrained online learning problems rely on two fundamental assumptions. We show how such assumptions can be circumvented by endowing standard primal-dual templates with weakly adaptive regret minimizers. We prove the first best-of-both-worlds no-regret guarantees which hold in absence of the two aforementioned assumptions.
  arXiv  Detail & Related papers  (2023-02-02T16:30:33Z)
• Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming [10.06803520598035]
  We develop a new approach to the problem called maximum optimality margin which the machine learning loss function by the optimality condition of the downstream optimization.
  arXiv  Detail & Related papers  (2023-01-26T17:53:38Z)
• Learning-Augmented Algorithms for Online Linear and Semidefinite Programming [9.849604820019394]
  Semidefinite programming (SDP) is a unifying framework that generalizes both linear and quadratically-constrained programming. There exist known impossibility results for approxing the optimal solution when constraints for covering SDPs arrive in an online fashion. We show that if the predictor is accurate, we can efficiently bypass these impossibility results and achieve a constant-factor approximation to the optimal solution.
  arXiv  Detail & Related papers  (2022-09-21T19:16:29Z)
• Faster Matchings via Learned Duals [31.61057940283721]
  We combine the idea of machine-learned predictions with the idea of "starting-warm" primal-dual algorithms. First, predicted duals may be infeasible, so we give an algorithm that efficiently maps predicted infeasible duals to nearby feasible solutions. Second, once the duals are feasible, they may not be optimal, so we show that they can be used to quickly find an optimal solution.
  arXiv  Detail & Related papers  (2021-07-20T21:11:09Z)
• Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms [85.97516436641533]
  We study the problem of improving the performance of online algorithms by incorporating machine-learned predictions. The goal is to design algorithms that are both consistent and robust. We provide the first set of non-trivial lower bounds for competitive analysis using machine-learned predictions.
  arXiv  Detail & Related papers  (2020-10-22T04:51:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.