Research map / Learning theory and algorithms / Combinatorial and search optimization
Submodular Meta-Learning
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 a shared initial set offline and add task-specific elements at test time | Submodular meta-learning · Ride Share Optimization | objective value | Helped |
| Learn a shared initial set offline and add task-specific elements at test time | Submodular meta-learning · Movie Recommendation | objective value | Helped |
| Use Meta-Greedy instead of choosing all elements during training | Submodular meta-learning · Ride Share Optimization | objective value | Helped |
| Use Meta-Greedy instead of choosing all elements during training | Submodular meta-learning · Movie Recommendation | objective value | Helped |
| Use Meta-Greedy instead of fully optimizing at test time | Submodular meta-learning · Ride Share Optimization | objective value | Hurt |
| Use Meta-Greedy instead of fully optimizing at test time | Submodular meta-learning · Movie Recommendation | objective value | Hurt |
| Increase the fraction of the set selected during training | Meta-Greedy · Ride Share Optimization | test-time computation | Helped |
| Increase the fraction of the set selected during training | Meta-Greedy · Ride Share Optimization | objective value | Mixed |
| Increase the task-specific portion selected at test time | Randomized Meta-Greedy · Ride Share Optimization | objective value | Helped |
| Use personalized task-specific selection rather than a training-only reduced ground set | Meta-Greedy versus Replacement-Greedy · Ride Share Optimization | objective value | Helped |
Closest papers by meaning
- Memory-Reduced Meta-Learning with Guaranteed Convergence (AAAI 2025 · similarity 0.90)
- Efficient Meta Learning via Minibatch Proximal Update (NeurIPS 2019 · similarity 0.90)
- Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate (ICLR 2022 · similarity 0.89)
- Modeling and Optimization Trade-off in Meta-learning (NeurIPS 2020 · similarity 0.89)
- More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms (ICML 2024 · similarity 0.89)
- Continuous-Time Meta-Learning with Forward Mode Differentiation (ICLR 2022 · similarity 0.89)
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.