Compute Less to Get More: Using ORC to Improve Sparse Filtering


  • Johannes Lederer Cornell University
  • Sergio Guadarrama University of California at Berkeley



sparse filtering, unsupervised feature learning, image classification


Sparse Filtering is a popular feature learning algorithm for image classification pipelines. In this paper, we connect the performance of Sparse Filtering with spectral properties of the corresponding feature matrices. This connection provides new insights into Sparse Filtering; in particular, it suggests early stopping of Sparse Filtering. We therefore introduce the Optimal Roundness Criterion (ORC), a novel stopping criterion for Sparse Filtering. We show that this stopping criterion is related with pre-processing procedures such as Statistical Whitening and demonstrate that it can make image classification with Sparse Filtering considerably faster and more accurate.




How to Cite

Lederer, J., & Guadarrama, S. (2015). Compute Less to Get More: Using ORC to Improve Sparse Filtering. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1).