Quote:
Originally Posted by ypeels
Another question about this figure: is there any intuition as to why regions of a given color (fixed overfit measure) are roughly linear in the stochastic Nsigma^2 graph, but nonlinear (exponential?) in the deterministic NQf graph (for Qf > 10)?
Thank you!

The analysis of the stochastic noise figure may be doable given the clean analytic components of the simulation (Legendre, pseudoinverse, Gaussian noise). In the deterministic noise figure, the noise value is quantified by the complexity of the target
. While deterministic noise (the part of
that cannot be captured by
) is indeed related to
, it is not necessarily linearly related to it so that direct parallel with what happens with stochastic noise does not hold.
BTW, the LaTeX stuff is done by delimiters [ math ] and [ /math ] (without the spaces) instead of $ and $. A bit cumbersome when you use a lot of math.