Abstract:
- Optimizing Functionals on the Space of Probabilities with Input Convex Neural Network - by David Alvarez-Melis, Yair Schiff, Youssef Mroueh
- Learning Revenue-Maximizing Auctions With Differentiable Matching - by Michael Curry, Uro Cornelius Lyi, Tom Goldstein, John P Dickerson
- Factored couplings in multi-marginal optimal transport via difference of convex programming - by Quang Huy Huy, Hicham Janati, Ievgen Redko, Rémi Flamary, Nicolas Courty
- Sinkhorn EM: An Expectation-Maximization algorithm based on entropic optimal transport - by Gonzalo E. Mena, Amin Nejatbakhsh, Erdem Varol, Jonathan Niles-Weed
- Subspace Detours Meet Gromov-Wasserstein - by Clément Bonet, Nicolas Courty, François Septier, Lucas Drumetz
- Input Convex Gradient Networks - by Jack Richter-Powell, Jonathan Peter Lorraine, Brandon Amos
- Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs - by Meyer Scetbon, Gabriel Peyré, Marco Cuturi
- Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe - by Thibault Sejourne, François-Xavier Vialard, Gabriel Peyré