方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 贝叶斯堆叠集成× | 高斯过程× | |
|---|---|---|
| 领域 | 机器学习 | 机器学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2018 | 2006 (book); roots in Kriging, 1951) |
| 提出者≠ | Yao, Y.; Vehtari, A.; Simpson, D.; Gelman, A. | Rasmussen, C. E. & Williams, C. K. I. |
| 类型≠ | Bayesian ensemble combination | Probabilistic non-parametric model |
| 开创性文献≠ | Yao, Y., Vehtari, A., Simpson, D., & Gelman, A. (2018). Using stacking to average Bayesian predictive distributions. Bayesian Analysis, 13(3), 917–1007. DOI ↗ | Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian Processes for Machine Learning. MIT Press. ISBN: 978-0-262-18253-9 |
| 别名 | Bayesian stacking, Bayesian model stacking, stacking with Bayesian weights, predictive distribution stacking | GP, Gaussian Process Regression, GPR, Kriging |
| 相关≠ | 6 | 3 |
| 摘要≠ | Bayesian stacking combines the predictive distributions of several base models by finding non-negative weights that maximise the leave-one-out log predictive score of the mixture. Formalised by Yao, Vehtari, Simpson, and Gelman (2018), it yields a single calibrated predictive distribution that is provably at least as good as any single constituent model under cross-validation. | A Gaussian Process (GP) is a non-parametric, fully probabilistic machine learning model that places a prior distribution directly over functions. Rather than predicting a single value, it returns a predictive mean and a calibrated uncertainty estimate at every test point, making it especially valuable for regression on small to medium datasets and for Bayesian optimization tasks. |
| ScholarGate数据集 ↗ |
|
|