原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
The previous trick works decently for modeling low-dimensional distributions. Unfortunately, this approach does not scale well to high-dimensions. The reason is that in order for our Monte Carlo estimate of the integral to be accurate, we may need many samples from pz, and the higher the dimensionality of z, the more samples we will typically need.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c033.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8