GitHub / dmivilensky / Sliding-for-Kernel-SVM

We consider a problem of minimizing a sum of two functions and propose a generic algorithmic framework (SAE) to separate oracle complexities for each function. We compare the performance of splitting accelerated enveloped accelerated variance reduced method with a different sliding technique.

JSON API: http://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dmivilensky%2FSliding-for-Kernel-SVM
PURL: pkg:github/dmivilensky/Sliding-for-Kernel-SVM

Topics: convex-optimization, kernel-svm, variance-reduction

• Files
• Readme
• Dependencies