Research map / Learning theory and algorithms / Submodular and game algorithms
A Learning-Augmented Approach to Online Allocation Problems
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies online allocation problems with learning-augmented (predicted) inputs, combining machine-learned advice with online algorithms to improve over worst-case guarantees.
Problem
Online allocation problems, where an algorithm must irrevocably choose options at each step that incur costs or rewards over d agents, and the objective is a function of accumulated per-agent totals; worst-case online algorithms are pessimistic.
Approach
Applies the learning-augmented (algorithms with predictions) framework to online allocation problems with d agents, using predictions to guide allocation decisions while retaining robustness guarantees; specific mechanism not stated in the abstract.
Closest papers by meaning
- Decoupling Learning and Decision-Making: Breaking the $\mathcal{O}(\sqrt{T})$ Barrier in Online Resource Allocation with First-Order Methods (ICML 2024 · similarity 0.87)
- Time Fairness in Online Knapsack Problems (ICLR 2024 · similarity 0.86)
- On the Universal Near Optimality of Hedge in Combinatorial Settings (NeurIPS 2025 · similarity 0.86)
- Augmenting Online Algorithms for Knapsack Problem with Total Weight Information (AAAI 2025 · similarity 0.86)
- Learning-Augmented Online Bidding in Stochastic Settings (NeurIPS 2025 · similarity 0.86)
- Learning-Augmented Algorithms for the Bahncard Problem (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.