Call for Contributions

Scope

We solicit submission of original research at the interface between optimal transport and machine learning, studying for instance (but not limited to):

  • numerical schemes to solve the OT problem in the discrete (fast EMD solvers), semi-discrete and continuous settings;
  • numerical and theoretical applications of OT to estimate generative models (e.g. minimum Kantorovich estimators / W-GAN / ABC procedures grounded on the Wasserstein geometry)
  • generalizations of the OT problem (e.g. multi-marginal OT, Gromov-Wasserstein matchings between metric spaces) and their applications;
  • theoretical results on approximations of OT distances through embeddings;
  • numerical resolution and theoretical study of relaxed / constrained / regularized OT problems;
  • applications of OT in supervised learning settings to handle histogram data (e.g. distance or kernel based classifiers, metric learning with the OT geometry);
  • applications of OT in unsupervised learning to summarize datasets (e.g. generalization of k-means type clustering, Wasserstein barycenters);
  • applications of OT to model interactions in social networks (e.g. matching models);
  • applications of OT to computer vision, graphics and related fields;
  • combinatorial perspectives on OT and related algebraic statistical concepts (e.g. contingency tables)

Authors can submit work that overlaps with previously published or submitted work, as long as it adds a new perspective on that work.

Submission Format

Submissions must adhere to NIPS 2017 style format available on the NIPS submission page. Papers may be between 6 and 10 pages long, including figures and references. Supplementary material can be provided. Submissions should not be anonymized.

Submission Process

Submissions should be uploaded on the OTML17 Easychair system before October 20, 23:59PM (PDT, Pacific Time). All papers will undergo a reviewing process.

Presentation of Accepted Contributions

All accepted papers will have a poster presentation and selected papers will be given oral presentation slots.