Entropic Gromov-Wasserstein between Gaussian Distributions
Khang Le, Dung Q. Le, Huy Nguyen, Dat Do, Tung Pham, Nhat Ho
Abstract
We study the entropic Gromov-Wasserstein and its unbalanced version between (unbalanced) Gaussian distributions with different dimensions. When the metric is the inner product, which we refer to as inner product Gromov-Wasserstein (IGW), we demonstrate that the optimal transportation plans of entropic IGW and its unbalanced variant are (unbalanced) Gaussian distributions. Via an application of von Neumann’s trace inequality, we obtain closed-form expressions for the entropic IGW between these Gaussian distributions. Finally, we consider an entropic inner product Gromov-Wasserstein barycenter of multiple Gaussian distributions. We prove that the barycenter is a Gaussian distribution when the entropic regularization parameter is small. We further derive a closed-form expression for the covariance matrix of the barycenter.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext c4ebfcf6-9204-4694-bbc5-6dd5d1e62a0dCited by top-tier papers4
- GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell GenomicsDominik Klein, Théo Uscidda, Fabian J. Theis, Marco CuturiNeurIPS 2024 · 34 citations
- Energy-Guided Continuous Entropic Barycenter Estimation for General CostsAlexander Kolesov, Petr Mokrov, Igor Udovichenko, Milena Gazdieva et al.NeurIPS 2024 · 13 citations
- Structure-Aware E(3)-Invariant Molecular Conformer Aggregation NetworksDuy Minh Ho Nguyen, Nina Lukashina, Tai Nguyen, An T. Le et al.ICML 2024 · 9 citations
- LoBCD-GW: A Fast and Data-Dependent Algorithm for Computing Gromov-Wasserstein Distance via Localized Block Coordinate DescentJingni Song, Jiawei Huang, Kangke Cheng, Bangxian Han et al.ICML 2026
Builds on7
- Graph Optimal Transport for Cross-Domain AlignmentLiqun Chen, Zhe Gan, Yu Cheng, Linjie Li et al.ICML 2020 · 193 citations
- Distributional Sliced-Wasserstein and Applications to Generative ModelingKhai Nguyen, Nhat Ho, Tung Pham, Hung BuiICLR 2021 · 111 citations
- Entropic Optimal Transport between Unbalanced Gaussian Measures has a Closed FormHicham Janati, Boris Muzellec, Gabriel Peyré, Marco CuturiNeurIPS 2020 · 109 citations
- The Unbalanced Gromov Wasserstein Distance: Conic Formulation and RelaxationThibault Séjourné, François-Xavier Vialard, Gabriel PeyréNeurIPS 2021 · 106 citations
- Point-set Distances for Learning Representations of 3D Point CloudsTrung Nguyen, Quang-Hieu Pham, Tam Le, Tung Pham et al.ICCV 2021 · 89 citations
Related papers
- Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descentJason M. Altschuler, Sinho Chewi, Patrik Gerber, Austin J. StrommeNeurIPS 2021 · 60 citations
- Debiased Sinkhorn barycentersHicham Janati, Marco Cuturi, Alexandre GramfortICML 2020 · 62 citations
- Computational Guarantees for Doubly Entropic Wasserstein BarycentersTomas Vaskevicius, Lénaïc ChizatNeurIPS 2023 · 5 citations
- Optimal Transport Barycenter via Nonconvex-Concave Minimax OptimizationKaheon Kim, Rentian Yao, Changbo Zhu, Xiaohui ChenICML 2025
- Partial Gromov-Wasserstein MetricYikun Bai, Rocio Diaz Martin, Abihith Kothapalli, Hengrong Du et al.ICLR 2025
