Efficient Robust Optimal Transport with Application to Multi-Label Classification

@article{Jawanpuria2020EfficientRO,
  title={Efficient Robust Optimal Transport with Application to Multi-Label Classification},
  author={Pratik Jawanpuria and N T V Satyadev and Bamdev Mishra},
  journal={2021 60th IEEE Conference on Decision and Control (CDC)},
  year={2020},
  pages={1490-1495}
}
Optimal transport (OT) is a powerful geometric tool for comparing two distributions and has been employed in various machine learning applications. In this work, we propose a novel OT formulation that takes feature correlations into account while learning the transport plan between two distributions. We model the feature-feature relationship via a symmetric positive semi-definite Mahalanobis metric in the OT cost function. For a certain class of regularizers on the metric, we show that the… 
[PDF] Semantic Reader
1 Citations
Background Citations
1

Figures and Tables from this paper

One Citation

On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry

It is shown that the Bures-Wasserstein geometry has a non-negative curvature, which further improves convergence rates of algorithms over the non-positively curved AI geometry, and it is verified that several popular cost functions are also geodesic convex under the BW geometry.

References

SHOWING 1-10 OF 42 REFERENCES

A Swiss Army Knife for Minimax Optimal Transport

This paper proposes to use a cutting-set method to solve the minimax OT problem and uses this method to define a notion of stability allowing us to select the ground metric robust to bounded perturbations.

Subspace Robust Wasserstein distances

This work proposes a "max-min" robust variant of the Wasserstein distance by considering the maximal possible distance that can be realized between two measures, assuming they can be projected orthogonally on a lower $k$-dimensional subspace.

Enriching Word Vectors with Subword Information

A new approach based on the skipgram model, where each word is represented as a bag of character n-grams, with words being represented as the sum of these representations, which achieves state-of-the-art performance on word similarity and analogy tasks.

Learning with a Wasserstein Loss

An efficient learning algorithm based on this regularization, as well as a novel extension of the Wasserstein distance from probability measures to unnormalized measures, which can encourage smoothness of the predictions with respect to a chosen metric on the output space.

Sinkhorn Distances: Lightspeed Computation of Optimal Transport

This work smooths the classic optimal transport problem with an entropic regularization term, and shows that the resulting optimum is also a distance which can be computed through Sinkhorn's matrix scaling algorithm at a speed that is several orders of magnitude faster than that of transport solvers.

SPOT: A framework for selection of prototypes using optimal transport

This work develops an optimal transport (OT) based framework to select informative prototypical examples that best represent a given target dataset and proposes an efficient greedy method that is both computationally fast and possess deterministic approximation guarantees.

Feature Robust Optimal Transport for High-dimensional Data

This paper proposes feature robust optimal transport (FROT) for high-dimensional data, which jointly solves feature selection and OT problems, and proposes using the FROT algorithm for the layer selection problem in deep neural networks for semantic correspondence.

Geometry-aware domain adaptation for unsupervised alignment of word embeddings

A novel manifold based geometric approach for learning unsupervised alignment of word embeddings between the source and the target languages by formulating the alignment learning problem as a domain adaptation problem over the manifold of doubly stochastic matrices.

Regularized Optimal Transport is Ground Cost Adversarial

This work proposes a new interpretation of regularization as a robust mechanism, and shows using Fenchel duality that any convex regularization of OT can be interpreted as ground cost adversarial, which incidentally gives access to a robust dissimilarity measure on the ground space, which can in turn be used in other applications.

Optimal Transport: Old and New

Couplings and changes of variables.- Three examples of coupling techniques.- The founding fathers of optimal transport.- Qualitative description of optimal transport.- Basic properties.- Cyclical…