1D and 2D learner: stop interpolating function instead of the loss #87
Description
(original issue on GitLab)
opened by Anton Akhmerov (@anton-akhmerov) at 2018-03-10T21:14:20.732Z
Right now as the user requests more points but does not provide any data, we update the learner's state by adding "fake" points with values interpolated using a linear approximation. In the cquad implementation we realized that this is conceptually not right, and instead we directly consider the loss of the children intervals a fraction of the parent loss.
Also in the 1D and 2D learner this would make more sense and would allow them to support arbitrary loss functions.
Related: gitlab:#50, gitlab:!34.