New Method Speeds Deep Gaussian Process Surrogates via Mini-Batch Latent MAP Estimation
Researchers propose mini-batch latent MAP estimation to make deep Gaussian process surrogates more efficient for modeling nonstationary response surfaces in computer experiments.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-30 04:00 · arXiv stat.ML
Efficient Deep Gaussian Process Surrogates via Mini-Batch Latent MAP Estimation