Corpus ID: 218869548

Feature Robust Optimal Transport for High-dimensional Data

@article{Petrovich2020FeatureRO,
  title={Feature Robust Optimal Transport for High-dimensional Data},
  author={Mathis Petrovich and Chao Liang and Yanbin Liu and Yao-Hung Hubert Tsai and Linchao Zhu and Y. Yang and R. Salakhutdinov and M. Yamada},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.12123}
}
Optimal transport is a machine learning problem with applications including distribution comparison, feature selection, and generative adversarial networks. In this paper, we propose feature robust optimal transport (FROT) for high-dimensional data, which jointly solves feature selection and OT problems. Specifically, we formulate the FROT problem as a min--max optimization problem. Then, we propose a convex formulation of FROT and solve it with the Frank--Wolfe-based optimization algorithm… Expand
2 Citations

Figures and Tables from this paper

References

SHOWING 1-10 OF 57 REFERENCES
Hyperpixel Flow: Semantic Correspondence With Multi-Layer Neural Features
SPair-71k: A Large-scale Benchmark for Semantic Correspondence
Subspace Robust Wasserstein distances
Sinkhorn Distances: Lightspeed Computation of Optimal Transport
The Earth Mover's Distance as a Metric for Image Retrieval
A Swiss Army Knife for Minimax Optimal Transport
A Kernel Two-Sample Test
A Kernel Statistical Test of Independence
Semantic Correspondence as an Optimal Transport Problem
...
1
2
3
4
5
...