Claudia Merger in joint work with Alexandre René, Kirsten Fischer and Peter Bouss
supervised by Moritz Helias and Carsten Honerkamp
in collaboration with David Dahmen and Christian Keup
data
INN
choose output
data distribution
data
INN
data
INN
sample
Gaussian
What has the INN learned?
Examples
data
INN
sample
INN must learn a approximate representation of data distribution.
How can we:
Order in polynomial increases exponentially.
Coefficients become large.
Order in polynomial increases exponentially.
Coefficients become large.
Strategy:
Order in polynomial increases exponentially.
Coefficients become large.
Strategy:
Affine coupling must also be able to decrease the order.
Affine coupling must also be able to decrease the order.
2nd order action
4th order action
sign change
Further investigations: