arXiv Machine Learning October 28, 2026 By Minh-Nhat Phung, Minh-Binh Tran

Regularized Unbalanced Optimal Transport with Pearson Marginal Penalties

Read the original on arXiv Machine Learning →

arXiv:2503. 15105v5 Announce Type: replace-cross Abstract: We study quadratically regularized unbalanced optimal transport with Pearson marginal penalties and a lower bound $\delta\ge0$ on the plan, including the sparse case $\delta=0$.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 1

Uniform Statistical Convergence of Empirical Sinkhorn Potentials with Exponential and Polynomial Dependence on the Regularization Parameter

arXiv:2608.29152v1 Announce Type: cross Abstract: We study the empirical Sinkhorn estimator of the entropic optimal transport potentials under the uniform loss. Since the potentials are only unique u...

By Denis Belomestny

arXiv Machine Learning

Aug 14

Sinkhorn Linearization and the Spectral Proxy: Unifying the Statistical and Algorithmic Theory of Feature-Parameterized Inverse Optimal Transport via a Single Spectral Sandwich

arXiv:2608. 13201v1 Announce Type: cross Abstract: We develop the statistical and algorithmic theory of inverse optimal transport (IOT) under the feature-parameterized cost C_theta(i,j) = -theta^T phi(i,j).

By Han Dong, Jiaming Li, Yongqiang Gong, Ruixi Li, Yin Liu

arXiv Machine Learning

Jul 23

Non-Asymptotic Variational Learning for Monotone Nonlinear Multiscale Elliptic Equations: Scale-Robust Primal-Dual Bounds and Strong-Form Statistical Ill-Conditioning

arXiv:2607. 15702v2 Announce Type: replace-cross Abstract: We develop a non-asymptotic approximation, sampling, and finite-iteration optimization theory for variational physics-informed approximation of uniformly monotone nonlinear multiscale elliptic equations.

By Ronald Katende

arXiv Machine Learning

Aug 31

SinkSLOT: Sinkhorn via Sparse Lifted Optimal Transport

arXiv:2608. 28262v1 Announce Type: new Abstract: Entropic optimal transport (EOT) has been shown to offer a computationally tractable approximation to exact optimal transport.

By Ian Hsieh, Soumya Snigdha Kundu, Tom Vercauteren, Reuben Dorent

benchmarks

arXiv Machine Learning

5d ago

Global $\mathcal{O}\left(k^{-2}\right)$ Convergence of Multilevel Gradient-Regularized Newton Methods

arXiv:2610. 35195v1 Announce Type: cross Abstract: We develop and analyze multilevel gradient-regularized Newton methods for unconstrained convex optimization with Lipschitz-continuous Hessians.

By Nick Tsipinakis, Matthias Voigt

arXiv Machine Learning

Aug 19

Spectrally Safe Neural Operator Warm-Starts for Large-Scale Newton Solvers

arXiv:2606. 21828v2 Announce Type: replace-cross Abstract: Neural operators are increasingly used to warm-start Newton solvers for nonlinear PDEs, on the premise that a low test error places the initial guess inside the basin of attraction.

By Jaemin Oh, Youngkyu Lee, Jerome Darbon, George Em Karniadakis

fine-tuning

One email a morning, machine-written

Related stories

Uniform Statistical Convergence of Empirical Sinkhorn Potentials with Exponential and Polynomial Dependence on the Regularization Parameter

Sinkhorn Linearization and the Spectral Proxy: Unifying the Statistical and Algorithmic Theory of Feature-Parameterized Inverse Optimal Transport via a Single Spectral Sandwich

Non-Asymptotic Variational Learning for Monotone Nonlinear Multiscale Elliptic Equations: Scale-Robust Primal-Dual Bounds and Strong-Form Statistical Ill-Conditioning

SinkSLOT: Sinkhorn via Sparse Lifted Optimal Transport

Global $\mathcal{O}\left(k^{-2}\right)$ Convergence of Multilevel Gradient-Regularized Newton Methods

Spectrally Safe Neural Operator Warm-Starts for Large-Scale Newton Solvers