Research map / Bandits and online learning / Online convex optimization and games
Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster $\text{L}$-/$\text{L}^\natural$-Convex Function Minimization
Shinsaku Sakaue, Taihei Oki
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 |
|---|---|---|---|
| Learn predictions by OGD on μ̄ (distance to set of all optimal solutions) instead of distance to a fixed optimal solution | prediction learning for L-/L♮-convex minimization · small random bipartite matching instances | number of Hungarian method iterations | Improved |
| Time bound uses distance to set of all optimal solutions (μ̄) rather than ℓ∞ distance to a fixed optimal solution | steepest descent warm-started by prediction · L-/L♮-convex minimization | time complexity bound | Improved |
| Online-to-batch sample complexity of learning predictions via OGD on μ̄ (regret C√(2nT)) | prediction learning · L-/L♮-convex function distribution | regret bound | No clear effect |
Closest papers by meaning
- Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with Predictions (NeurIPS 2022 · similarity 0.91)
- Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing (ICML 2024 · similarity 0.87)
- A Generalization Result for Convergence in Learning-to-Optimize (ICML 2025 · similarity 0.86)
- Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods (ICLR 2025 · similarity 0.86)
- Learning-Augmented Approximation Algorithms for Maximum Cut and Related Problems (NeurIPS 2024 · similarity 0.86)
- Random Function Descent (NeurIPS 2024 · 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.
