0.25
0.5
0.75
1.25
1.5
1.75
2
A Survey of Model-Based Methods for Global Optimization
Published on May 31, 20162901 Views
This article describes model-based methods for global optimization. After introducing the global optimization framework, modeling approaches for stochastic algorithms are presented. We differentiate
Related categories
Chapter list
A Survey of Model-based Methods for Global Optimization00:00
Surrogates00:00
Surrogates: Popular metamodeling techniques - 100:53
Surrogates: Popular metamodeling techniques - 202:28
Applications of SBO03:17
Applications of Metamodels and Multi-fidelity Approximation04:01
Surrogate-assisted Evolutionary Algorithms - 105:02
Surrogate-assisted Evolutionary Algorithms - 205:23
Multiple Models05:58
Multiple Models: Ensembles06:53
Overview - Quality Criteria: How to Select Surrogates07:25
Model Refinement: Selection Criteria for Sample Points08:00
Model Selection Criteria09:22
Single or Ensemble10:40
Criteria for Selecting a Surrogate10:58
Overview - Examples12:04
Criteria for Selecting a Surrogate: Evolvability12:06
Evolvability Learning of Surrogates13:02
Evolvability14:13
SPO - 217:12
SPO - 117:52
SPO - 318:01
SPO - 419:42
SPO - 521:07
Why are Ensembles Better?34:17
Untitled35:35
A Simple Machine Learning Example - 236:40
Correlation37:22
Beyond Averaging: Stacking38:23
2-fold Stacking38:59
Stacking: Considerations53:41
Blending and Meta-Meta Models55:23
“Frankenstein Ensembles"58:02
Summary: Structure and Interpretation of Computer Programs (SICP)59:56