`

( events)   Timezone: »  
Workshop
Mon Dec 13 05:00 AM -- 01:00 PM (PST)
Optimal Transport and Machine Learning
Jason Altschuler · Charlotte Bunne · Laetitia Chapel · Marco Cuturi · Rémi Flamary · Gabriel Peyré · Alexandra Suvorikova





Workshop Home Page

Over the last few years, optimal transport (OT) has quickly become a central topic in machine learning. OT is now routinely used in many areas of ML, ranging from the theoretical use of OT flow for controlling learning algorithms to the inference of high-dimensional cell trajectories in genomics. The Optimal Transport and Machine Learning (OTML) workshop series (in '14, '17, '19) has been instrumental in shaping this research thread. For this new installment of OTML, we aim even bigger by hosting an exceptional keynote speaker, Alessio Figalli, who received the 2018 Fields Medal for his breakthroughs in the analysis of the regularity properties of OT. OTML will be a unique opportunity for cross-fertilization between recent advances in pure mathematics and challenging high-dimensional learning problems.

TBA (Plenary talk)
Implicit Riemannian Concave Potential Maps (Oral)
Regularity theory of optimal transport maps (Plenary talk)
Generative adversarial learning with adapted distances (Keynote talk)
8 5min-spotlight presentations (Spotlight posters)
Poster session - 1 (Poster session)
TBA (Plenary talk)
Optimal transport and probability flows (Keynote talk)
Graphical Optimal Transport and its applications (Keynote talk)
Poster session - 2 (Poster session)
TBA (Keynote talk)
Entropic estimation of optimal transport maps (Oral)
Discrete Schr\¨odinger Bridges with Applications to Two-Sample Homogeneity Testing (Oral)
Benefits of using optimal transport in computational learning and inversion (Keynote talk)
Concluding remarks (Discussion)
Poster session - 3 (Poster session)
Input Convex Gradient Networks (Spotlight)
On Combining Expert Demonstrations in Imitation Learning via Optimal Transport (Poster)
Sinkhorn EM: An Expectation-Maximizationalgorithm based on entropic optimal transport (Poster)
Input Convex Gradient Networks (Poster)
Optimal Transport losses and Sinkhorn algorithm with general convex regularization (Poster)
Optimizing Functionals on the Space of Probabilities with Input Convex Neural Network (Poster)
Multistage Monge Kantorovich Problem applied to optimal ecological transition (Poster)
Sliced Multi-Marginal Optimal Transport (Poster)
Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs (Spotlight)
Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe (Spotlight)
Dual Regularized Optimal Transport (Poster)
Discrete Schr\"odinger Bridges with Applications to Two-Sample Homogeneity Testing (Oral)
Learning Revenue-Maximizing Auctions With Differentiable Matching (Spotlight)
Entropic estimation of optimal transport maps (Poster)
Learning Revenue-Maximizing Auctions With Differentiable Matching (Poster)
Subspace Detours Meet Gromov-Wasserstein (Spotlight)
Gradient flows on graphons: existence, convergence, continuity equations (Poster)
Wasserstein Adversarially Regularized Graph Autoencoder (Poster)
Sinkhorn EM: An Expectation-Maximizationalgorithm based on entropic optimal transport (Spotlight)
Likelihood Training of Schrödinger Bridges using Forward-Backward SDEs Theory (Poster)
Linear Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport (Poster)
Discrete Schr\"odinger Bridges with Applications to Two-Sample Homogeneity Testing (Poster)
Entropic estimation of optimal transport maps (Oral)
Measuring association with Wasserstein distances (Poster)
Learning Single-Cell Perturbation Responses using Neural Optimal Transport (Poster)
Towards interpretable contrastive word mover's embedding (Poster)
Implicit Riemannian Concave Potential Maps (Oral)
Towards an FFT for measures (Poster)
Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe (Poster)
Efficient estimates of optimal transport via low-dimensional embeddings (Poster)
On the complexity of the optimal transport problem with graph-structured cost (Poster)
Implicit Riemannian Concave Potential Maps (Poster)
Factored couplings in multi-marginal optimal transport via difference of convex programming (Spotlight)
Variational Wasserstein gradient flow (Poster)
Central Limit Theorems for Multidimensional Wasserstein Distances (Poster)
Optimizing Functionals on the Space of Probabilities with Input Convex Neural Network (Spotlight)
Factored couplings in multi-marginal optimal transport via difference of convex programming (Poster)
Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs (Poster)
Cross-Domain Lossy Compression as Optimal Transport with an Entropy Bottleneck (Poster)
Subspace Detours Meet Gromov-Wasserstein (Poster)