Multi-Marginal Optimal Transport and Probabilistic Graphical Models

DOI10.1109/TIT.2021.3077465zbMATH Open1475.49057arXiv2006.14113MaRDI QIDQ5001817FDOQ5001817

Authors: Isabel Haasler, Rahul Singh, Qinsheng Zhang, Johan Karlsson, Yongxin Chen 

Publication date: 23 July 2021

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: We study multi-marginal optimal transport problems from a probabilistic graphical model perspective. We point out an elegant connection between the two when the underlying cost for optimal transport allows a graph structure. In particular, an entropy regularized multi-marginal optimal transport is equivalent to a Bayesian marginal inference problem for probabilistic graphical models with the additional requirement that some of the marginal distributions are specified. This relation on the one hand extends the optimal transport as well as the probabilistic graphical model theories, and on the other hand leads to fast algorithms for multi-marginal optimal transport by leveraging the well-developed algorithms in Bayesian inference. Several numerical examples are provided to highlight the results.

Full work available at URL: https://arxiv.org/abs/2006.14113

Recommendations

• Multi-marginal optimal transport: theory and applications
• Optimal transport and variational Bayesian inference
• Inference With Aggregate Data in Probabilistic Graphical Models: An Optimal Transport Approach
• THE MULTI-MARGINAL OPTIMAL PARTIAL TRANSPORT PROBLEM
• Multi-marginal optimal transport on Riemannian manifolds
• Empirical regularized optimal transport: statistical theory and applications
• Optimal transport for generative models
• Optimal transport: fast probabilistic approximation with exact solvers
• Solutions to multi-marginal optimal transport problems concentrated on several graphs
• A multi-objective interpretation of optimal transport

zbMATH Keywords

probabilistic graphical modelsentropy regularized multi-marginal optimal transport

Mathematics Subject Classification ID

Optimal transportation (49Q22) Probabilistic graphical models (62H22) Transportation, logistics and supply chain management (90B06)

Cited In (15)

• Low-Rank Tensor Approximations for Solving Multimarginal Optimal Transport Problems
• Polynomial-time algorithms for multimarginal optimal transport problems with structure
• Efficient and exact multimarginal optimal transport with pairwise costs
• Graph-structured tensor optimization for nonlinear density control and mean field games
• Monge-Kantorovich optimal transport through constrictions and flow-rate constraints
• Wasserstein Barycenters Are NP-Hard to Compute
• Minimum information dependence modeling
• State estimation and structure identification of complex networks with time-varying delays and model uncertainty based on probabilistic graph neural network
• Multimarginal Optimal Transport with a Tree-Structured Cost and the Schrödinger Bridge Problem
• Inference With Aggregate Data in Probabilistic Graphical Models: An Optimal Transport Approach
• Distributionally robust optimization using optimal transport for Gaussian mixture models
• Hardness results for multimarginal optimal transport problems
• A family of pairwise multi-marginal optimal transports that define a generalized metric
• Learning hidden Markov models from aggregate observations
• Feedback particle filter for collective inference

This page was built for publication: Multi-Marginal Optimal Transport and Probabilistic Graphical Models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5001817)