André Heinrich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
André Heinrich has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Radu Ioan Boţ
Faculty of Mathematics, University of Vienna, Vienna, Austria
5 shared publications - Ernö Robert Csetnek
Department of Mathematics, Chemnitz University of Technology, Chemnitz, Germany
2 shared publications - Christopher Hendrich
Chemnitz University of Technology
1 shared publication - Ernö Robert Csetnek
Faculty of Mathematics, University of Vienna, Vienna, Austria
1 shared publication - Gert Wanka
Faculty of Mathematics, Chemnitz University of Technology, Chemnitz, Germany
1 shared publication
Latest Publications
- 26 February 2014
- Published by Springer Nature in Mathematical Programming
- Vol. 150 (2) , 251-279
On the convergence rate improvement of a primal-dual splitting algorithm for solving monotone inclusion problems
- 26 February 2014
- Published by Springer Nature in Mathematical Programming
- Vol. 150 (2) , 251-279
On the convergence rate improvement of a primal-dual splitting algorithm for solving monotone inclusion problems
- Open Access
- 21 November 2013
- Published by Walter de Gruyter GmbH in Open Mathematics
- Vol. 12 (2) , 381-394
Employing different loss functions for the classification of images via supervised learning
Supervised learning methods are powerful techniques to learn a function from a given set of labeled data, the so-called training data. In this paper the support vector machines approach is applied to an image classification task. Starting with the corresponding Tikhonov regularization problem, reformulated as a convex optimization problem, we introduce a conjugate dual problem to it and prove that, whenever strong duality holds, the function to be learned can be expressed via the dual optimal solutions. Corresponding dual problems are then derived for different loss functions. The theoretical results are applied by numerically solving a classification task using high dimensional real-world data in order to obtain optimal classifiers. The results demonstrate the excellent performance of support vector classification for this particular problem.
- 21 November 2013
- Published by Walter de Gruyter GmbH in Open Mathematics
- Vol. 12 (2) , 381-394
Open AccessEmploying different loss functions for the classification of images via supervised learning
Supervised learning methods are powerful techniques to learn a function from a given set of labeled data, the so-called training data. In this paper the support vector machines approach is applied to an image classification task. Starting with the corresponding Tikhonov regularization problem, reformulated as a convex optimization problem, we introduce a conjugate dual problem to it and prove that, whenever strong duality holds, the function to be learned can be expressed via the dual optimal solutions. Corresponding dual problems are then derived for different loss functions. The theoretical results are applied by numerically solving a classification task using high dimensional real-world data in order to obtain optimal classifiers. The results demonstrate the excellent performance of support vector classification for this particular problem.
- Open Access
On the convergence rate improvement of a primal-dual splitting algorithm for solving monotone inclusion problems
We present two modified versions of the primal-dual splitting algorithm relying on forward-backward splitting proposed in \cite{vu} for solving monotone inclusion problems. Under strong monotonicity assumptions for some of the operators involved we obtain for the sequences of iterates that approach the solution orders of convergence of O(1/n) and O(\omega^n), for $\omega \in (0,1)$, respectively. The investigated primal-dual algorithms are fully decomposable, in the sense that the operators are processed individually at each iteration. We also discuss the modified algorithms in the context of convex optimization problems and present numerical experiments in image processing and support vector machines classification.Open AccessOn the convergence rate improvement of a primal-dual splitting algorithm for solving monotone inclusion problems
We present two modified versions of the primal-dual splitting algorithm relying on forward-backward splitting proposed in \cite{vu} for solving monotone inclusion problems. Under strong monotonicity assumptions for some of the operators involved we obtain for the sequences of iterates that approach the solution orders of convergence of O(1/n) and O(\omega^n), for $\omega \in (0,1)$, respectively. The investigated primal-dual algorithms are fully decomposable, in the sense that the operators are processed individually at each iteration. We also discuss the modified algorithms in the context of convex optimization problems and present numerical experiments in image processing and support vector machines classification. - 16 January 2013
- Published by Springer Nature in Annals of Operations Research
- Vol. 222 (1) , 197-211
Regression tasks in machine learning via Fenchel duality
- 16 January 2013
- Published by Springer Nature in Annals of Operations Research
- Vol. 222 (1) , 197-211
Regression tasks in machine learning via Fenchel duality
- Open Access
A primal-dual splitting algorithm for finding zeros of sums of maximally monotone operators
We consider the primal problem of finding the zeros of the sum of a maximally monotone operator with the composition of another maximally monotone operator with a linear continuous operator and a corresponding dual problem formulated by means of the inverse operators. A primal-dual splitting algorithm which simultaneously solves the two problems in finite-dimensional spaces is presented. The scheme uses at each iteration separately the resolvents of the maximally monotone operators involved and it gives rise to a splitting algorithm for finding the zeros of the sum of compositions of maximally monotone operators with linear continuous operators. The iterative schemes are used for solving nondifferentiable convex optimization problems arising in image processing and in location theory.
Open AccessA primal-dual splitting algorithm for finding zeros of sums of maximally monotone operators
We consider the primal problem of finding the zeros of the sum of a maximally monotone operator with the composition of another maximally monotone operator with a linear continuous operator and a corresponding dual problem formulated by means of the inverse operators. A primal-dual splitting algorithm which simultaneously solves the two problems in finite-dimensional spaces is presented. The scheme uses at each iteration separately the resolvents of the maximally monotone operators involved and it gives rise to a splitting algorithm for finding the zeros of the sum of compositions of maximally monotone operators with linear continuous operators. The iterative schemes are used for solving nondifferentiable convex optimization problems arising in image processing and in location theory.