Research map / Learning theory and algorithms / Prediction and decision losses
Gaussian Process-Based Real-Time Learning for Safety Critical Applications
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 |
|---|---|---|---|
| Replace exact sequential GP with LoG-GP tree aggregation (MoE variant) | GP regression for real-time learning · SARCOS, buzz, electric regression | average update time: updates up to 10 times faster than existing streaming methods | Helped |
| Use locally active GP aggregation with MoE/gPoE/rBCM LoG-GP variants | GP prediction · SARCOS, buzz, electric regression | average prediction time: comparable to ISSGP (about 0.12-0.19 ms vs 0.16-0.19 ms) | No clear effect |
| Use MoE-LoG-GP instead of vanilla GP in event-triggered control | event-triggered learning control on pendulum · pendulum control simulation | number of learning events: 1741 events vs 1310 for vanilla GP | Hurt |
| Use MoE-LoG-GP instead of vanilla GP in event-triggered control | event-triggered learning control on pendulum · pendulum control simulation | real-time feasibility of prediction/update times: vanilla GP exceeds inter-event time after about t=120s; LoG-GP stays fast enough | Helped |
Closest papers by meaning
- Asynchronous Distributed Gaussian Process Regression (AAAI 2025 · similarity 0.87)
- Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel (NeurIPS 2024 · similarity 0.86)
- Error Bounds for Gaussian Process Regression Under Bounded Support Noise with Applications to Safety Certification (AAAI 2025 · similarity 0.85)
- Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes (NeurIPS 2024 · similarity 0.85)
- Learning Safe Control via On-the-Fly Bandit Exploration (ICML 2025 · similarity 0.84)
- Distributionally Robust Active Learning for Gaussian Process Regression (ICML 2025 · 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.