Research map / Learning theory and algorithms / Sample complexity
Adversarially Robust Optimization with Gaussian Processes
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 StableOpt's robust upper-confidence-bound selection and lower-confidence-bound perturbation sampling | GP optimization with adversarial perturbations · Synthetic function | ε-regret | Helped |
| Use StableOpt rather than the compared baseline methods | Robust optimization of Lake Zürich chlorophyll data · Lake Zürich chlorophyll data | ε-regret | Helped |
| Use StableOpt for robust optimization across two possible target locations | Robot pushing · Robust robot pushing | Robust objective | Helped |
| Use StableOpt to select a group by its worst-case movie preference | MovieLens-100K group recommendation · MovieLens-100K test users | ε-regret | Helped |
| Optimize the ordinary global maximum instead of the adversarially stable objective | GP-UCB · Adversarially robust GP optimization | ε-regret | Hurt |
| Use the same robust optimistic point for both sampling and reporting, without pessimistic perturbation sampling | MaxiMin-GP-UCB · Adversarially robust GP optimization | ε-regret | Hurt |
Closest papers by meaning
- Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks (NeurIPS 2025 · similarity 0.92)
- Robust and Computation-Aware Gaussian Processes (NeurIPS 2025 · similarity 0.89)
- On Lower Bounds for Standard and Robust Gaussian Process Bandit Optimization (ICML 2021 · similarity 0.88)
- Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits (NeurIPS 2025 · similarity 0.88)
- Improved Regret Bounds for Gaussian Process Upper Confidence Bound in Bayesian Optimization (NeurIPS 2025 · similarity 0.86)
- Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance (ICML 2025 · 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.