Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 39 min ago
Peer-reviewedLicence not statedThe Annals of Probability

Wasserstein mirror gradient flow as the limit of the Sinkhorn algorithm

  1. 1Department of Econometrics and Statistics, University of Chicago
  2. 2Department of Mathematics, University of British Columbia
  3. 3Department of Mathematics, University of Washington

Related

  1. Averaged Mirror Descent and Dual Gradient Methods: Convergent Algorithms for Entropic Gromov-Wasserstein Problems
    Joanna Marks, Gabriel Rioux, Riccardo Passeggeri
    arXivPreprintarXiv licenceFull textOptimisation & controlarXiv
  2. Exponential Convergence of the Sinkhorn Algorithm for the Schrödinger Bridge with Regime Switching
    Katharina Eichinger, Anna Kazeykina, Zhenjie Ren +1
    HALPreprintLicence not statedGeneral mathematicsHAL
  3. Exponential convergence of Sinkhorn algorithm for entropy martingale optimal transport
    Anna Kazeykina, Zhenjie Ren, Hecheng Wang
    arXivPreprintarXiv licenceFull textOptimisation & controlProbabilityarXiv
  4. A Provably Convergent and Practical Algorithm for Gromov--Wasserstein Optimal Transport
    Ling Liang, Lei Yang
    arXivPreprintarXiv licenceFull textOptimisation & controlarXiv
  5. Control Strategies for Multi-Species Wasserstein Gradient Flows
    Dante Kalise, Lucas M. Moschen, Grigorios A. Pavliotis
    arXivPreprintCC BY 4.0Full textAnalysis & PDEsNumerical analysis & scientific computingarXiv
BibTeX
@article{deb2026wasserstein,
  title = {{Wasserstein mirror gradient flow as the limit of the Sinkhorn algorithm}},
  author = {Nabarun Deb and Young‐Heon Kim and Soumik Pal and Geoffrey R. Schiebinger},
  journal = {The Annals of Probability},
  year = {2026},
  month = aug,
  doi = {10.1214/25-aop1801},
  url = {https://arxiv.org/abs/2307.16421},
}
RIS
TY  - JOUR
TI  - Wasserstein mirror gradient flow as the limit of the Sinkhorn algorithm
AU  - Nabarun Deb
AU  - Young‐Heon Kim
AU  - Soumik Pal
AU  - Geoffrey R. Schiebinger
PY  - 2026
DA  - 2026/08/28
JO  - The Annals of Probability
DO  - 10.1214/25-aop1801
UR  - https://arxiv.org/abs/2307.16421
SN  - 0091-1798
SN  - 2168-894X
ER  -