Research map / Learning theory and algorithms / Sample complexity
Discrete-Convex-Analysis-Based Framework for Warm-Starting Algorithms with Predictions
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 |
|---|---|---|---|
| Bound warm-start iterations using the \ell_\infty distance between prediction and optimum | DCA-based warm-start for weighted perfect bipartite matching · Weighted perfect bipartite matching | time complexity: \mathrm{O}(m\sqrt{n}\norm{\hat{p} - p^*}_1) -> \mathrm{O}(m\sqrt{n}\norm{p^* - \hat{p}}_\infty) | Improved |
| Learn predictions by minimizing expected \ell_\infty error rather than expected \ell_1 error | Prediction learning · Batch prediction learning | sample complexity: \mathrm{O}(C^2n^3\log n) -> \mathrm{O}(C^2n) | Improved |
Closest papers by meaning
- Rethinking Warm-Starts with Predictions: Learning Predictions Close to Sets of Optimal Solutions for Faster $\text{L}$-/$\text{L}^\natural$-Convex Function Minimization (ICML 2023 · similarity 0.91)
- Faster Matchings via Learned Duals (NeurIPS 2021 · similarity 0.87)
- Pairwise Matching Through Max-Weight Bipartite Belief Propagation (CVPR 2016 · similarity 0.85)
- Memory-Constrained Algorithms for Convex Optimization (NeurIPS 2023 · similarity 0.85)
- Complexity of Discrete Energy Minimization Problems (ECCV 2016 · similarity 0.84)
- Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing (ICML 2024 · similarity 0.84)
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.
