 |
Conference papers
Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions
Abstract : We design simple screening tests to automatically discard data samples in empirical risk minimization without losing optimization guarantees. We derive loss functions that produce dual objectives with a sparse solution. We also show how to regularize convex losses to ensure such a dual sparsity-inducing property, and propose a general method to design screening tests for classification or regression based on ellipsoidal approximations of the optimal set. In addition to producing computational gains, our approach also allows us to compress a dataset into a subset of representative points.
Cited literature [29 references]
https://hal.archives-ouvertes.fr/hal-02395624
Contributor : Grégoire Mialon <>
Submitted on : Friday, June 12, 2020 - 3:46:18 PM
Last modification on : Friday, July 10, 2020 - 7:48:03 AM
Contributor : Grégoire Mialon <>
Submitted on : Friday, June 12, 2020 - 3:46:18 PM
Last modification on : Friday, July 10, 2020 - 7:48:03 AM
File
main_aistats.pdf
Files produced by the author(s)
