# Dual-to-kernel learning with ideals

@article{Kirly2014DualtokernelLW, title={Dual-to-kernel learning with ideals}, author={F. Kir{\'a}ly and M. Kreuzer and Louis Theran}, journal={ArXiv}, year={2014}, volume={abs/1402.0099} }

In this paper, we propose a theory which unifies kernel learning and symbolic algebraic methods. We show that both worlds are inherently dual to each other, and we use this duality to combine the structure-awareness of algebraic methods with the efficiency and generality of kernels. The main idea lies in relating polynomial rings to feature space, and ideals to manifolds, then exploiting this generative-discriminative duality on kernel matrices. We illustrate this by proposing two algorithms… CONTINUE READING

4 Citations

The algebraic combinatorial approach for low-rank matrix completion

- Computer Science, Mathematics
- 2015

- 78
- PDF

#### References

##### Publications referenced by this paper.

SHOWING 1-10 OF 29 REFERENCES

Nonlinear dimensionality reduction by locally linear embedding.

- Medicine, Computer Science
- 2000

- 12,555
- PDF

Nonlinear Component Analysis as a Kernel Eigenvalue Problem

- Mathematics, Computer Science
- 1998

- 7,261
- PDF

The Nature of Statistical Learning Theory

- Mathematics, Political Science
- 2000

- 36,400
- Highly Influential
- PDF

The Construction of Multivariate Polynomials with Preassigned Zeros

- Mathematics, Computer Science
- 1982

- 175