paper-with-me

Papers

Faster Unbalanced Optimal Transport: Translation invariant Sinkhorn and 1-D Frank-Wolfe

2022-01-03 · Thibault Séjourné, François-Xavier Vialard, Gabriel Peyré

Unbalanced optimal transport (UOT) extends optimal transport (OT) to take into account mass variations to compare distributions. This is crucial to make OT successful in ML applications, making it robust to data normalization and outliers. The baseline algorithm is Sinkhorn, but its convergence speed might be significantly slower for UOT than for OT. In this work, we identify the cause for this deficiency, namely the lack of a global normalization of the iterates, which equivalently corresponds to a translation of the dual OT potentials. Our first contribution leverages this idea to develop a provably accelerated Sinkhorn algorithm (coined 'translation invariant Sinkhorn') for UOT, bridging the computational gap with OT. Our second contribution focusses on 1-D UOT and proposes a Frank-Wolfe solver applied to this translation invariant formulation. The linear oracle of each steps amounts to solving a 1-D OT problems, resulting in a linear time complexity per iteration. Our last contribution extends this method to the computation of UOT barycenter of 1-D measures. Numerical simulations showcase the convergence speed improvement brought by these three approaches.

📄 PDF Abstract BibTeX arXiv:2201.00730

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Sample complexity of unbalanced entropic OT

2026-06-23 · Francisco Andrade, Gabriel Peyré, Clarice Poon arxiv

Optimal transport (OT) has become a central language for comparing probability measures, but exact balanced OT is often both too rigid for data with missing, created, or destroyed mass and subject to unfavorable high-dim…

Unbalanced Feature Transport for Exemplar-based Image Translation

2021-06-19 · CVPR 2021 1 · Fangneng Zhan, Yingchen Yu, Kaiwen Cui, Gongjie Zhang 외

Despite the great success of GANs in images translation with different conditioned inputs such as semantic segmentation and edge maps, generating high-fidelity realistic images with reference styles remains a grand chall…

Image-to-Image TranslationSemantic SegmentationTranslation

WFR-MFM: One-Step Inference for Dynamic Unbalanced Optimal Transport

2026-01-28 · Xinyu Wang, Ruoyu Wang, Qiangwei Peng, Peijie Zhou 외 arxiv

Reconstructing dynamical evolution from limited observations is a fundamental challenge in single-cell biology, where dynamic unbalanced optimal transport provides a principled framework for modeling coupled transport an…

Scalable Simulation-free Entropic Unbalanced Optimal Transport

2024-10-03 · Jaemoo Choi, Jaewoong Choi

The Optimal Transport (OT) problem investigates a transport map that connects two distributions while minimizing a given cost function. Finding such a transport map has diverse applications in machine learning, such as g…

Image-to-Image TranslationTranslation

Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs

2025-05-21 · Sonia Mazelet, Rémi Flamary, Bertrand Thirion

Optimal transport between graphs, based on Gromov-Wasserstein and other extensions, is a powerful tool for comparing and aligning graph structures. However, solving the associated non-convex optimization problems is comp…

Stochastic Block Model