Bayesian Optimization by 2023

Bayesian Optimization by 2023

Author:2023
Language: eng
Format: epub


Chapter 4 Gaussian proCess reGression with GpytorCh

Figure 4-2. Visualizing the initial ten noisy observations

Before fitting a GP model, we must define the mean and covariance (kernel) functions for the prior GP. There are multiple mean functions available in GPyTorch, including the zero mean function gpytorch.means.ZeroMean(), the constant mean function gpytorch.means.

ConstantMean(), and the linear mean function gpytorch.means.LinearMean(). In this case, we use the constant mean function, assuming that there is no systematic trend in the data.

As for the kernel function, we choose one of the most widely used kernels: the RBF

x x 2

kernel, or the squared exponential kernel k x x

1

2

, exp

, where l is the

1

2



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.