Coulomb Classi ers: Reinterpreting SVMs as Electrostatic Systems

By Sepp Hochreiter, Michael C. Mozer

Subfields: Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical Learning Theory

1. Klaus Obermayer
2. Sepp Hochreiter
3. Michael C. Mozer
4. Hubert Ramsauer
5. Günter Klambauer
6. Martin Heusel
7. Thomas Unterthiner
8. Bernhard Nessler

Citations in the corpus

• Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields (2017, background): “Another related work is the Potential Support Vector Machine (PSVM), which minimizes Coulomb potential differences [21, 22].”
• Coulomb Classifiers: Generalizing Support Vector Machines via an Analogy to Electrostatic Systems (2002, methodology): “The C{SVM requires that P i yi i = 0; although this constraint may not be ful lled in the system described here, it can be enforced by a slightly di erent system [3].”