Sinkhorn Divergence

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Unbalanced W-Flow: Unbalanced Wasserstein Drifting under Finite-Batch Marginal Fluctuations
Oct 13, 2026Jongwook Jeon, Mingue Park, Jiwon Choi +3One-Step Generative Modeling Flow-Based Generative Modeling
Yonsei University · KAIST
A Local Sinkhorn Framework for Conditional Distribution Reconstruction of Multidimensional Random Fields
Aug 12, 2026Mingtao Xia, Qijing ShenUncertainty Quantification Sinkhorn Divergence
School of Mathematics, University of Birmingham, Watson Building, Edgbaston, Birmingham, B15 2TT, United Kingdom · Department of Mathematics, University of Houston, 3551 Cullen Blvd, Houston, 77204, Texas, United States · Nuffield Department of Medicine, University of Oxford, United Kingdom, Old Road Campus, Oxford, OX3 7BN, United Kingdom
Generative Distributionally Robust Optimization
Jul 27, 2026Ziwei Zhang, Jonathan Yu-Meng Li, Zhihao JinSinkhorn Divergence Distributionally Robust Optimization
1Telfer School of Management, University of Ottawa · Department of Electrical and Computer Engineering, Western University
On the convergence of graph Laplacians with a symmetric divergence
Jul 7, 2026Liane XuSinkhorn Divergence Manifold Learning
Program in Applied and Computational Mathematics, Princeton University
Spherical Harmonic Optimal Transport: Application to Climate Models Comparisons
May 18, 2026Pierre Houédry, Iskander Legheraba, Léo Buecher +1Sinkhorn Divergence Kernel Methods
INRIA Rennes · LPHI, UMR 5294, CNRS, INSERM · IRISA, UMR 6074, CNRS
Sinkhorn Treatment Effects: A Causal Optimal Transport Measure
May 8, 2026Medha Agarwal, Alex LuedtkeCausal Effect Estimation Sinkhorn Divergence
Department of Statistics, University of Washington, Seattle, WA, USA · Department of Health Care Policy, Harvard Medical School, Boston, MA, USA
On the Wasserstein Gradient Flow Interpretation of Drifting Models
May 6, 2026Arthur Gretton, Li Kevin Wenliang, Alexandre Galashov +3Wasserstein Gradient Flows Sinkhorn Divergence
Google DeepMind
Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics
Mar 21, 2026Aratrika Mustafi, Soumya MukherjeeSinkhorn Divergence Associative Memory
Department of Statistics, Pennsylvania State University
Sinkhorn-Drifting Generative Models
Mar 12, 2026Ping He, Om Khangaonkar, Hamed Pirsiavash +2Sinkhorn Divergence Drifting Models
Department of Computer Science, Vanderbilt University · Department of Computer Science, University of California, Davis · Department of Computer Science, Purdue University

Oct 13, 2026J/K move · Enter open · S save

Unbalanced W-Flow: Unbalanced Wasserstein Drifting under Finite-Batch Marginal Fluctuations

Jongwook Jeon, Mingue Park, Jiwon Choi, Jaihoon Kim+2

Yonsei University · KAIST

One-Step Generative Modeling Flow-Based Generative Modeling Optimal Transport Sinkhorn Divergence

Open paper AskPDF arXiv

Teacher-free one-step generative models such as W-Flow learn directly from distributional objectives, with the Sinkhorn divergence providing the strongest empirical performance among the energies studied in W-Flow. However, Sinkhorn divergence is based on balanced optimal transport, whose exact marginal constraints can induce undesirable transport under finite minibatch fluctuations. We introduce UW-Flow, which replaces the balanced Sinkhorn energy with a debiased unbalanced Sinkhorn divergence and derives the corresponding Wasserstein velocity. The resulting dynamics retain W-Flow's cross-minus-self structure, recover the balanced limit, and preserve target identifiability under suitable assumptions. We further characterize the finite-batch velocity error of balanced and unbalanced transport by comparing each minibatch field with its population counterpart. Our analysis identifies conditions under which marginal relaxation yields smaller minibatch-to-population velocity error, and shows that for separated matched modes, balanced sensitivity grows with inter-mode separation while the corresponding Unbalanced Optimal Transport (UOT) sensitivity remains controlled by local transport geometry. Controlled experiments on fixed-support and continuous two-mode distributions support these predictions. On MNIST, CIFAR-10, and ImageNet-100, UW-Flow improves generation under matched training budgets, with the largest gains in unconditional generation and consistent improvements in the class-conditional setting.