Feature uncertainty bounding schemes for large robust nonlinear SVM classifiers
This work addresses robust classification for large datasets with bounded uncertainties, presenting an incremental improvement in handling feature uncertainties in nonlinear SVMs.
The paper tackles binary classification with large, uncertain data by formulating a robust nonlinear SVM training problem, proposing two uncertainty bounding schemes for random approximate features and achieving solutions via efficient stochastic approximation techniques.
We consider the binary classification problem when data are large and subject to unknown but bounded uncertainties. We address the problem by formulating the nonlinear support vector machine training problem with robust optimization. To do so, we analyze and propose two bounding schemes for uncertainties associated to random approximate features in low dimensional spaces. The proposed techniques are based on Random Fourier Features and the Nyström methods. The resulting formulations can be solved with efficient stochastic approximation techniques such as stochastic (sub)-gradient, stochastic proximal gradient techniques or their variants.