Research map / Probabilistic and scientific modeling / Bayesian optimization
Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces
Hung Tran-The, Sunil Gupta, Santu Rana, Huong Ha, Svetha Venkatesh
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 |
|---|---|---|---|
| Use hyperharmonic expansion and shift the search space toward the best point found so far | HuBO · Benchmark functions, low dimensions | log distance to true optimum | Improved |
| Use hyperharmonic expansion and shift the search space toward the best point found so far | HuBO · Elastic Net on MNIST | prediction accuracy | Improved |
| Restrict acquisition optimisation to a growing set of small hypercubes | HD-HuBO · Benchmark functions, high dimensions | log distance to true optimum | Improved |
| Restrict acquisition optimisation to a growing set of small hypercubes | HD-HuBO · Elastic Net on MNIST | prediction accuracy | Hurt |
| Use HD-HuBO for neural-network parameter optimisation | Two-layer neural network · MNIST validation dataset | validation loss | Improved |
| Use smaller α, including α = -1 rather than α = -0.95 or α = -0.9 (ablation) | HuBO · 5-dim Ackley | regret | Improved |
| Increase λ from 0.2 or 0.5 to 1 (ablation) | HD-HuBO · High-dimensional Ackley | regret | Improved |
Closest papers by meaning
- Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal (NeurIPS 2024 · similarity 0.92)
- Principled Preferential Bayesian Optimization (ICML 2024 · similarity 0.90)
- BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability (NeurIPS 2026 · similarity 0.90)
- Stopping Bayesian Optimization with Probabilistic Regret Bounds (NeurIPS 2024 · similarity 0.90)
- Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization (ICLR 2024 · similarity 0.90)
- Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds (ICML 2024 · 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.
