Welcome to the homepage of the

Mathematical Optimization for Data Science Group

Department of Mathematics and Computer Science, Saarland University, Germany

Techniques for gradient based bilevel optimization with nonsmooth lower level problems

P. Ochs, R. Ranftl, T. Brox and T. Pock

Abstract:
We propose techniques for approximating bilevel optimization problems with non-smooth and non-unique lower level problems. The key is the substitution of the lower level minimization problem with an iterative algorithm that is guaranteed to converge to a minimizer of the problem. Using suitable non-linear proximal distance functions, the update mappings of such an iterative algorithm can be differentiable, notwithstanding the fact that the minimization problem is non-smooth. This technique for smoothly approximating the solution map of the lower level problem raises several questions that are discussed in this paper.
pdf Bibtex Publisher's link
Citation:
P. Ochs, R. Ranftl, T. Brox, T. Pock:
Techniques for gradient based bilevel optimization with nonsmooth lower level problems. [pdf]
Journal of Mathematical Imaging and Vision, 56(2):175-194, 2016. (Invited Paper)
Bibtex:
@article{ORBP16,
  title        = {Techniques for gradient based bilevel optimization with nonsmooth lower level problems},
  author       = {P. Ochs and R. Ranftl and T. Brox and T. Pock},
  year         = {2016},
  journal      = {Journal of Mathematical Imaging and Vision},
  number       = {2},
  volume       = {56},
  pages        = {175--194}
}


MOP Group
©2017-2024
The author is not
responsible for
the content of
external pages.