Confusion in Random Feature Posterior

zi-w / Max-value-Entropy-Search

Max-value Entropy Search for Efficient Bayesian Optimization

MIT License

68 stars 17 forks source link

Confusion in Random Feature Posterior #2

Closed ssydasheng closed 5 years ago

ssydasheng commented 6 years ago

https://github.com/zi-w/Max-value-Entropy-Search/blob/885030574233c95891ddbfb23ff0a8cb1790fe5a/utils/sampleMaximumValues.m#L47

What's the use for this line? D itself is already the eigendecomposition of Z^t Z + \sigma^2 I, it looks to me that R=1./D. Can you please clarify this ?

zi-w commented 5 years ago

Hi, you can find the detailed explanation of this method at Appendix B.2 of http://www.jmlr.org/papers/volume9/seeger08a/seeger08a.pdf