Exploiting Gradients in Bayesian Inference of Expensive Simulators
In such cases, a Bayesian optimization-based active learning approach with Gaussian process surrogate models has been used to maximize the information obtained from a limited simulation budget.
ProofPaper ↗
Key points
- Simulators based on differential equations are ubiquitous in science and engineering.
- Recently, gradients of simulator outputs with respect to input parameters have become increasingly available, yet they are rarely exploited for inference.
- In this paper, we demonstrate how incorporating gradient information into the Gaussian process surrogate accelerates Bayesian optimization-based inference under a limited simulation budget.
- Our results show significant improvement in convergence speed from using gradient information.
Sources (1)
- [1]Exploiting Gradients in Bayesian Inference of Expensive SimulatorsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 02:52 PM
In such cases, a Bayesian optimization-based active learning approach with Gaussian process surrogate models has been used to maximize the information obtained from a limited simulation budget.
Simulators based on differential equations are ubiquitous in science and engineering.
Extractive summary: sentences quoted from the sources.