Department of Mathematics
 Search | Help | Login | pdf version | printable version

Math @ Duke



Publications [#322689] of Guillermo Sapiro

Papers Published

  1. Huang, J; Qiu, Q; Sapiro, G; Calderbank, R, Discriminative robust transformation learning, Advances in Neural Information Processing Systems, vol. 2015-January (January, 2015), pp. 1333-1341
    (last updated on 2019/06/26)

    This paper proposes a framework for learning features that are robust to data variation, which is particularly important when only a limited number of training samples are available. The framework makes it possible to tradeoff the discriminative value of learned features against the generalization error of the learning algorithm. Robustness is achieved by encouraging the transform that maps data to features to be a local isometry. This geometric property is shown to improve (K, ∈)-robustness, thereby providing theoretical justification for reductions in generalization error observed in experiments. The proposed optimization framework is used to train standard learning algorithms such as deep neural networks. Experimental results obtained on benchmark datasets, such as labeled faces in the wild, demonstrate the value of being able to balance discrimination and robustness.
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320