Workshop
Mon Dec 13 05:00 AM -- 01:00 PM (PST)
Optimal Transport and Machine Learning
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.
| Optimal Transport in the Biomedical Sciences: Challenges and Opportunities (Plenary talk) | |
| Implicit Riemannian Concave Potential Maps (Oral) | |
| Regularity theory of optimal transport maps (Plenary talk) | |
| Generative adversarial learning with adapted distances (Keynote talk) | |
| Spotlight Presentations | |
| Poster Session | |
| Entropic Regularization of Optimal Transport as a Statistical Regularization (Plenary talk) | |
| Optimal transport and probability flows (Keynote talk) | |
| Graphical Optimal Transport and its applications (Keynote talk) | |
| Poster Session | |
| Enabling integrated analysis of single-cell multi-omic datasets with optimal transport (Keynote talk) | |
| Entropic estimation of optimal transport maps (Oral) | |
| Discrete Schrödinger 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 and social interaction (Poster session) | |
| On the complexity of the optimal transport problem with graph-structured cost (Poster) | |
| Subspace Detours Meet Gromov-Wasserstein (Poster) | |
| Measuring association with Wasserstein distances (Poster) | |
| Sinkhorn EM: An Expectation-Maximization algorithm based on entropic optimal transport (Poster) | |
| Factored couplings in multi-marginal optimal transport via difference of convex programming (Poster) | |
| Discrete Schrödinger Bridges with Applications to Two-Sample Homogeneity Testing (Poster) | |
| Learning Revenue-Maximizing Auctions With Differentiable Matching (Poster) | |
| Entropic estimation of optimal transport maps (Poster) | |
| A Central Limit Theorems for Multidimensional Wasserstein Distances (Poster) | |
| Discrete Schrödinger Bridges with Applications to Two-Sample Homogeneity Testing (Oral) | |
| Towards an FFT for measures (Poster) | |
| Sliced Multi-Marginal Optimal Transport (Poster) | |
| Implicit Riemannian Concave Potential Maps (Poster) | |
| Towards interpretable contrastive word mover's embedding (Poster) | |
| Multistage Monge Kantorovich Problem applied to optimal ecological transition (Poster) | |
| Wasserstein Adversarially Regularized Graph Autoencoder (Poster) | |
| Likelihood Training of Schrödinger Bridges using Forward-Backward SDEs Theory (Poster) | |
| Efficient estimates of optimal transport via low-dimensional embeddings (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) | |
| Dual Regularized Optimal Transport (Poster) | |
| Input Convex Gradient Networks (Spotlight) | |
| Entropic estimation of optimal transport maps (Oral) | |
| Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe (Spotlight) | |
| On Combining Expert Demonstrations in Imitation Learning via Optimal Transport (Poster) | |
| Sinkhorn EM: An Expectation-Maximizationalgorithm based on entropic optimal transport (Spotlight) | |
| Factored couplings in multi-marginal optimal transport via difference of convex programming (Spotlight) | |
| Learning Revenue-Maximizing Auctions With Differentiable Matching (Spotlight) | |
| Optimizing Functionals on the Space of Probabilities with Input Convex Neural Network (Spotlight) | |
| Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs (Spotlight) | |
| Subspace Detours Meet Gromov-Wasserstein (Spotlight) | |
| Variational Wasserstein gradient flow (Poster) | |
| Linear Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport (Poster) | |
| Implicit Riemannian Concave Potential Maps (Oral) | |
| Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe (Poster) | |
| Gradient flows on graphons: existence, convergence, continuity equations (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) | |
| Learning Single-Cell Perturbation Responses using Neural Optimal Transport (Poster) | |
| Input Convex Gradient Networks (Poster) | |