Skip to main navigation Skip to search Skip to main content

Constrained Online Convex Optimization with Memory and Predictions

  • Mohammed Abdullah
  • , George Iosifidis
  • , Salah Eddine Elayoubi
  • , Tijani Chahed
  • L2S, CNRS, Univ Paris-Sud
  • Telecom Sudparis
  • Delft University of Technology

Research output: Contribution to journalConference articlepeer-review

Abstract

We study Constrained Online Convex Optimization with Memory (COCO-M), where both the loss and the constraints depend on a finite window of past decisions made by the learner. This setting extends the previously studied unconstrained online optimization with memory framework and captures practical problems such as the control of constrained dynamical systems and scheduling with reconfiguration budgets. For this problem, we propose the first algorithms that achieve sublinear regret and sublinear cumulative constraint violation under time-varying constraints, both with and without predictions of future loss and constraint functions. Without predictions, we introduce an adaptive penalty approach that guarantees sublinear regret and constraint violation. When short-horizon and potentially unreliable predictions are available, we reinterpret the problem as online learning with delayed feedback and design an optimistic algorithm whose performance improves as prediction accuracy improves, while remaining robust when predictions are inaccurate. Our results bridge the gap between classical constrained online convex optimization and memory-dependent settings, and provide a versatile learning toolbox with diverse applications.

Original languageEnglish
Pages (from-to)19524-19532
Number of pages9
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume40
Issue number24
DOIs
Publication statusPublished - 1 Jan 2026
Event40th AAAI Conference on Artificial Intelligence, AAAI 2026 - Singapore, Singapore
Duration: 20 Jan 202627 Jan 2026

Fingerprint

Dive into the research topics of 'Constrained Online Convex Optimization with Memory and Predictions'. Together they form a unique fingerprint.

Cite this