• Corpus ID: 13936913

LEARNING WITH INFINITELY MANY KERNELS VIA SEMI-INFINITE PROGRAMMING

@inproceedings{Weber2008LEARNINGWI,
  title={LEARNING WITH INFINITELY MANY KERNELS VIA SEMI-INFINITE PROGRAMMING},
  author={G Weber},
  year={2008}
}
Abstract: In recent years, learning methods are desirable because of their reliability and efficiency in real-world problems. We propose a novel method to find infinitely many kernel combinations for learning problems with the help of infinite and semi-infinite optimization regarding all elements in kernel space. This will provide to study variations of combinations of kernels when considering heterogeneous data in real-world applications. Looking at all infinitesimally fine convex combinations… 

Figures from this paper

MODELLING OF KERNEL MACHINES BY INFINITE AND SEMI‐INFINITE PROGRAMMING

This work proposes a novel method of “infinite” kernel combinations for learning problems with the help of infinite and semi‐infinite programming regarding all elements in kernel space.

On numerical optimization theory of infinite kernel learning

The results show that the new algorithm called “infinite” kernel learning (IKL) on heterogenous data sets improves the classifaction accuracy efficiently on heterogeneous data compared to classical one-kernel approaches.

Non-Sparse Regularization and Efficient Training with Multiple Kernels

Improvements in MKL have finally made MKL fit for deployment to practical applications: MKL now has a good chance of improving the accuracy (over a plain sum kernel) at an affordable computational cost.

Non-Sparse Regularization for Multiple Kernel Learning

Empirical applications of p-norm MKL to three real-world problems from computational biology show that non-sparse MKL achieves accuracies that go beyond the state-of-the-art.

Norm Multiple Kernel Learning

Empirical applications of lp-norm MKL to three real-world problems from computational biology show that non-sparse MKL achieves accuracies that surpass the state-of-the-art, and two efficient interleaved optimization strategies for arbitrary norms are developed.

` p-Norm Multiple Kernel Learning

P-norm MKL to three real-world problems from computational biology show that non-sparse MKL achieves accuracies that surpass the state-of-the-art, and two efficient interleaved optimization strategies for arbitrary norms are developed.

Learning with infinitely many features

A principled framework for learning with infinitely many features, situations that are usually induced by continuously parametrized feature extraction methods, and it is shown that using Fourier-based features, it is possible to perform approximate infinite kernel learning.

Optimality Conditions for Convex Semi-infinite Programming Problems with Finitely Representable Compact Index Sets

In the present paper, we analyze a class of convex semi-infinite programming problems with arbitrary index sets defined by a finite number of nonlinear inequalities. The analysis is carried out by

Optimality Conditions for Convex Semi-infinite Programming Problems with Finitely Representable Compact Index Sets

This paper analyzes a class of convex semi-infinite programming problems with arbitrary index sets defined by a finite number of nonlinear inequalities by employing the constructive approach, which relies on the notions of immobile indices and their immobility orders.

Multiple Kernel Learning Algorithms

Overall, using multiple kernels instead of a single one is useful and it is believed that combining kernels in a nonlinear or data-dependent way seems more promising than linear combination in fusing information provided by simple linear kernels, whereas linear methods are more reasonable when combining complex Gaussian kernels.

References

SHOWING 1-10 OF 26 REFERENCES

Multiple kernel learning, conic duality, and the SMO algorithm

Experimental results are presented that show that the proposed novel dual formulation of the QCQP as a second-order cone programming problem is significantly more efficient than the general-purpose interior point methods available in current optimization toolboxes.

Large Scale Multiple Kernel Learning

It is shown that the proposed multiple kernel learning algorithm can be rewritten as a semi-infinite linear program that can be efficiently solved by recycling the standard SVM implementations, and generalize the formulation and the method to a larger class of problems, including regression and one-class classification.

Linear Semi-Infinite Optimization

MODELLING. Modelling with the Primal Problem. Modelling with the Dual Problem. LINEAR SEMI-INFINITE SYSTEMS. Alternative Theorems. Consistency. Geometry. Stability. THEORY OF LINEAR SEMI-INFINITE

An Introduction to Support Vector Machines and Other Kernel-based Learning Methods

This is the first comprehensive introduction to Support Vector Machines (SVMs), a new generation learning system based on recent advances in statistical learning theory, and will guide practitioners to updated literature, new applications, and on-line software.

Pattern Analysis for the Prediction of Eukoryatic Pro-peptide Cleavage Sites ?

An application that will allow the prediction of the pro-peptide cleavage site of fungal extracellular proteins which display mostly a monobasic or dibasic processing site is developed and a novel approach that simultaneously performs model selection together with the test of accuracy and testing confidence levels is introduced.

Charakterisierung struktureller stabilit at in der nichtlinearen optimierung

  • Augustinus publishing house (now: Mainz publishing house)
  • 1992