Research map / Probabilistic and scientific modeling / Bayesian optimization
Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces
Leonard Papenmeier, Luigi Nardi, Matthias Poloczek
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 Bounce instead of competing optimizers | High-dimensional combinatorial and mixed-space optimization · LABS | best objective value | Improved |
| Use Bounce instead of competing optimizers | High-dimensional combinatorial and mixed-space optimization · ClusterExpansion | total negative weight of clauses | Improved |
| Use Bounce instead of competing optimizers | High-dimensional combinatorial and mixed-space optimization · PestControl | objective value | Improved |
| Use Bounce instead of competing optimizers | High-dimensional combinatorial and mixed-space optimization · SVM | held-out RMSE | No clear effect |
| Use Bounce instead of competing optimizers | High-dimensional combinatorial and mixed-space optimization · Ackley53 | best objective value | Improved |
| Use Bounce instead of competing optimizers | High-dimensional combinatorial and mixed-space optimization · Contamination | objective value | No clear effect |
| Use Bounce instead of competing optimizers | High-dimensional combinatorial and mixed-space optimization · MaxSAT60 | samples to find an optimal assignment | Improved |
| Use larger parallel batches | Bounce · Mixed and combinatorial benchmarks | objective value per batch | Improved |
| Replace the previous trust-region management with Bounce's dynamic-budget strategy (ablation) | Bounce · Discrete and mixed benchmarks | objective value | Improved |
| Replace the previous trust-region management with Bounce's dynamic-budget strategy (ablation) | Bounce · Continuous benchmarks | objective value | Mixed |
| Remove random signs and random category offsets to bias toward low-sequency solutions (ablation) | Bounce · Original benchmarks | best objective value | Improved |
| Remove random signs and random category offsets to bias toward low-sequency solutions (ablation) | Bounce · Randomized benchmarks | best objective value | No clear effect |
Closest papers by meaning
- Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization (NeurIPS 2025 · similarity 0.89)
- BOIDS: High-Dimensional Bayesian Optimization via Incumbent-Guided Direction Lines and Subspace Embeddings (AAAI 2025 · similarity 0.86)
- A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences (NeurIPS 2024 · similarity 0.86)
- Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization (ICLR 2024 · similarity 0.85)
- Monte Carlo Tree Search based Space Transfer for Black Box Optimization (NeurIPS 2024 · similarity 0.85)
- Vanilla Bayesian Optimization Performs Great in High Dimensions (ICML 2024 · similarity 0.85)
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.
