Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Embedded Bandits for Large-Scale Black-Box Optimization
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 |
|---|---|---|---|
| Use EmbeddedHunter instead of RESOO or SRESOO | Large-scale black-box optimization · Ellipsoid, FletcherPowell, Rosenbrock, and Ackley | best solution quality | Helped |
| Increase the function-evaluation budget (ablation) | EmbeddedHunter · Ellipsoid, FletcherPowell, Rosenbrock, and Ackley | best solution quality | Helped |
| Increase explicit problem dimensionality (ablation) | EmbeddedHunter · Scalability experiment | best solution quality | Hurt |
| Increase the number of independent random-embedding runs (ablation) | RESOO · Embedding Number experiment | best solution quality | Helped |
| Increase the number of independent random-embedding runs (ablation) | SRESOO · Embedding Number experiment | best solution quality | No clear effect |
| Vary the evaluation-allocation factor M (ablation) | EmbeddedHunter · Embedding Number experiment | regret | Mixed |
| Increase effective dimensionality (ablation) | Random-embedding algorithms, including EmbeddedHunter · Effective Dimension experiment | best solution quality | Hurt |
| Increase the mismatch between the embedding dimension and actual effective dimension (ablation) | EmbeddedHunter · Effective Dimension Knowledge experiment | best solution quality | Hurt |
Closest papers by meaning
- Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization (NeurIPS 2020 · similarity 0.84)
- High-dimensional Linear Bandits with Knapsacks (ICML 2024 · similarity 0.84)
- Procrastinated Tree Search: Black-Box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback (AAAI 2022 · similarity 0.84)
- Optimization Can Learn Johnson Lindenstrauss Embeddings (NeurIPS 2024 · similarity 0.83)
- Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints (NeurIPS 2024 · similarity 0.83)
- Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit (NeurIPS 2024 · similarity 0.83)
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.