Multi-Merge Budget Maintenance for Stochastic Gradient Descent SVM Training

no code implementations • 26 Jun 2018 • Sahar Qaadan, Tobias Glasmachers

Budgeted Stochastic Gradient Descent (BSGD) is a state-of-the-art technique for training large-scale kernelized support vector machines.

Dual SVM Training on a Budget

no code implementations • 26 Jun 2018 • Sahar Qaadan, Merlin Schüler, Tobias Glasmachers

We present a dual subspace ascent algorithm for support vector machine training that respects a budget constraint limiting the number of support vectors.

Speeding Up Budgeted Stochastic Gradient Descent SVM Training with Precomputed Golden Section Search

no code implementations • 26 Jun 2018 • Tobias Glasmachers, Sahar Qaadan

Limiting the model size of a kernel support vector machine to a pre-defined budget is a well-established technique that allows to scale SVM learning and prediction to large-scale data.