Employing different loss functions for the classification of images via supervised learning
Linear operators and ill-posed problems, regularization (47A52) Duality theory (optimization) (49N15) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies for image processing (68U10) Convex programming (90C25) Stochastic learning and adaptive control (93E35)
In this paper, the support vector machines approach is applied to an image classification task. To this end, the authors reformulate the general Tikhonov regularization problem, to which the supervised learning problem gives rise, as a convex (not necessarily differentiable) optimization problem. They construct a conjugate dual to it, prove under suitable qualification conditions the existence of strong duality and express the optimal solutions of the primal problem via the ones of the dual. This has as a consequence the formulation of the decision function to be learned by means of the optimal solutions of the dual. Hence for the specific learning task one only has to numerically solve the dual problem, which, different to the primal one, can be mainly formulated as a convex differentiable optimization problem.
- 10.1162/153244303322753733
- A Compendium to Ensure Computational Reproducibility in High-Dimensional Classification Tasks
- A primal-dual splitting algorithm for finding zeros of sums of maximal monotone operators
- An introduction to support vector machines and other kernel-based learning methods.
- Classification with Gaussians and convex loss
- Conjugate duality in convex optimization
- Convex Analysis
- D-ADMM: A Communication-Efficient Distributed Algorithm for Separable Optimization
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- How to compare different loss functions and their risks
- scientific article; zbMATH DE number 1727434 (Why is no real title available?)
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 3551792 (Why is no real title available?)
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- scientific article; zbMATH DE number 823069 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- Optimization problems in statistical learning: duality and optimality conditions
- Sparsity and Smoothness Via the Fused Lasso
- Support vector machines with different norms: Motivation, formulations and results
- Theory of Reproducing Kernels
- Value regularization and Fenchel duality
- A variable smoothing algorithm for solving convex optimization problems
- A preference optimization based unifying framework for supervised learning problems
- Regression tasks in machine learning via Fenchel duality
- Analysis of loss functions in support vector machines
- A novel multi-scale loss function for classification problems in machine learning
- Generalization of cross-entropy loss function for image classification
This page was built for publication: Employing different loss functions for the classification of images via supervised learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2440581)
