We introduce the notion of learning from contradictions, a.k.a Universum learning, for multiclass problems and propose a novel formulation for multiclass universum SVM (MU-SVM). We show that learning from contradictions (using MU-SVM) incurs lower sample complexity compared to multiclass SVM (M-SVM) by deriving the Natarajan dimension for sample complexity for PAC-learnability of MU-SVM. We also propose an analytic span bound for MU-SVM and demonstrate its utility for model selection resulting in ~ 2 - 4× faster computation times than standard resampling techniques. We empirically demonstrate the efficacy of MU-SVM on several real world datasets achieving > 20% improvement in test accuracies compared to M-SVM. Insights into the underlying behavior of MU-SVM using a histograms-of-projections method are also provided.
|Original language||English (US)|
|Journal||Advances in Neural Information Processing Systems|
|State||Published - 2019|
|Event||33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019 - Vancouver, Canada|
Duration: Dec 8 2019 → Dec 14 2019