Kirill Chernyshev

@yunfeihaha, I leaved a PR, discussing resulting image, check it out, maybe you'll find it useful

Second example incorrectly computing mean -- variable `distances` has shape `(512, )`, which is number of dimensions, not number of vectors. Changing in `linalg.norm` parameter `axis` from 0 to 1...

`KDTree`'s [init_node function](https://github.com/scikit-learn/scikit-learn/blob/main/sklearn/neighbors/_kd_tree.pyx#L39) comments describe part of an algorithm dealing with `Node` attributes very well. In [bound computation](https://github.com/scikit-learn/scikit-learn/blob/main/sklearn/neighbors/_kd_tree.pyx#L58) "faster queries" are mentioned, and [radius assignment](https://github.com/scikit-learn/scikit-learn/blob/main/sklearn/neighbors/_kd_tree.pyx#L77) makes reference to usage in...

Since the links above not available, put here relevant ones: https://diffeq.sciml.ai/stable/analysis/parameter_estimation/#parameter_estimation https://diffeq.sciml.ai/stable/analysis/parameter_estimation/#The-Problem-Generator-Function https://diffeq.sciml.ai/stable/analysis/parameter_estimation/#Note-About-Loss-Functions