Research map / Learning theory and algorithms / Prediction and decision losses
Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 promising parameter regions from instance samples rather than uniformly sample the parameter space | B&B configuration with optimal parameters in (a,b) · B&B configuration problem | sample complexity: (2^n/\epsilon')^2 versus \tilde O((\delta\eta)^{-2}) | Helped |
| Use data-dependent partition complexity and capped losses to learn a finite candidate set | Infinite piecewise-constant configuration spaces · Piecewise-constant configuration problems | sample complexity per round: \tilde O\left(\frac{d \ln |\textsc{Partition}(\sample_t, c \cdot OPT_{\delta/4})| + c\cdot OPT_{\delta/4}}{\eta^2\delta^ | Helped |
Closest papers by meaning
- A Generalization Result for Convergence in Learning-to-Optimize (ICML 2025 · similarity 0.85)
- What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization (NeurIPS 2025 · similarity 0.85)
- A geometric framework for momentum-based optimizers for low-rank training (NeurIPS 2025 · similarity 0.85)
- Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework (NeurIPS 2025 · similarity 0.85)
- Solver-Free Decision-Focused Learning for Linear Optimization Problems (NeurIPS 2025 · similarity 0.85)
- BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability (NeurIPS 2026 · 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.