Mathematical Optimization for Data Science Group, Saarland University

Welcome to the homepage of the

Mathematical Optimization for Data Science Group

Department of Mathematics and Computer Science, Saarland University, Germany

Home
Teaching
Research
Publications
Job Offers

Saarland
University

Mathematics
and

Computer Science

Differentiating the Value Function by using Convex Duality

S. Mehmood and P. Ochs

Abstract:
We consider the differentiation of the value function for parametric optimization problems. Such problems are ubiquitous in Machine Learning applications such as structured support vector machines, matrix factorization and min-min or minimax problems in general. Existing approaches for computing the derivative rely on strong assumptions of the parametric function. Therefore, in several scenarios there is no theoretical evidence that a given algorithmic differentiation strategy computes the true gradient information of the value function. We leverage a well known result from convex duality theory to relax the conditions and to derive convergence rates of the derivative approximation for several classes of parametric optimization problems in Machine Learning. We demonstrate the versatility of our approach in several experiments, including non-smooth parametric functions. Even in settings where other approaches are applicable, our duality based strategy shows a favorable performance.



pdf	Bibtex	arXiv

Latest update: 27.12.2020

Citation:
S. Mehmood, P. Ochs:
Differentiating the Value Function by using Convex Duality.

International Conference on Artificial Intelligence and Statistics, 2021.

Bibtex:
@inproceedings{MO21, title = {Differentiating the Value Function by using Convex Duality}, author = {S. Mehmood and P. Ochs}, year = {2021}, booktitle = {International Conference on Artificial Intelligence and Statistics}, }

Impressum
Datenschutz