Sciweavers

Share
SCALESPACE
2015
Springer

Bilevel Optimization with Nonsmooth Lower Level Problems

3 years 6 months ago
Bilevel Optimization with Nonsmooth Lower Level Problems
We consider a bilevel optimization approach for parameter learning in nonsmooth variational models. Existing approaches solve this problem by applying implicit differentiation to a sufficiently smooth approximation of the nondifferentiable lower level problem. We propose an alternative method based on differentiating the iterations of a nonlinear primal–dual algorithm. Our method computes exact (sub)gradients and can be applied also in the nonsmooth setting. We show preliminary results for the case of multi-label image segmentation.
Peter Ochs, René Ranftl, Thomas Brox, Thoma
Added 17 Apr 2016
Updated 17 Apr 2016
Type Journal
Year 2015
Where SCALESPACE
Authors Peter Ochs, René Ranftl, Thomas Brox, Thomas Pock
Comments (0)
books