Research map / Bandits and online learning / Online convex optimization and games
Faster Fundamental Graph Algorithms via Learned Predictions
Justin Chen, Sandeep Silwal, Ali Vakilian, Fred Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Initialize matching with predicted duals rather than starting from scratch | Hungarian algorithm on foreign-exchange-derived matching instances · Foreign-exchange shortest-path-to-matching instances, 2020–2021 | Hungarian algorithm iterations: up to an order of magnitude reduction | Improved |
| Use prior-month optimal duals rather than the training-set median duals | Hungarian algorithm on foreign-exchange-derived matching instances · Foreign-exchange shortest-path-to-matching instances, 2020–2021 | Hungarian algorithm iterations | Improved |
| Use less accurate predicted duals | Hungarian algorithm on foreign-exchange-derived matching instances · Foreign-exchange shortest-path-to-matching instances, batch setting | Hungarian iterations saved | Hurt |
Closest papers by meaning
- Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS (ICML 2024 · similarity 0.88)
- Improved Approximations for Hard Graph Problems using Predictions (ICML 2025 · similarity 0.87)
- Polynomial Time Learning Augmented Algorithms for NP-hard Permutation Problems (ICML 2025 · similarity 0.86)
- Approximation algorithms for combinatorial optimization with predictions (ICLR 2025 · similarity 0.86)
- Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph (ICML 2024 · similarity 0.86)
- Algorithms and Hardness for Active Learning on Graphs (ICML 2025 · similarity 0.85)
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.
