Derives the cold Sinkhorn limiting dynamics as tau approaches zero, proving finite-time convergence to unregularized OT and improved O(tau^{-1}) iteration complexity for dual suboptimality.
Sinkhorn divergences for unbalanced optimal transport
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
years
2026 8representative citing papers
Proves sharp O(1/k) rate for Sinkhorn via local bipartite graph analysis of positive-mass edges, bootstrapped from prior almost-sharp global bound.
TimeLAVA values time series segments by marginal contribution to minimizing distributional discrepancy using selective wavelet transforms and unbalanced optimal transport, without model training.
Proves finite-sample bounds for the optimal coupling in unbalanced entropic OT via compactness and strong convexity of a translation-invariant dual.
Heat kernel Sinkhorn algorithm on the 2-sphere converges to OT cost with O(n) memory and O(n^{3/2}) time per iteration, retaining geometric properties and applied to climate model evaluation.
Debiasable ground costs lift to debiasable OT/EOT/MMD costs under negative-definiteness or continuous positive-semidefinite kernel conditions, via an inf-representation that also yields barycentric and interpolation formulas.
DRIO adds worst-case Wasserstein regularization to time series imputation, yielding a tractable adversarial surrogate and alternating algorithm that improves robustness under missingness.
RECAST reconstructs black-box models under limited data by treating counterfactuals as class samples within a Wasserstein geometry framework to preserve surrogate fidelity without online access.
citing papers explorer
-
Effective dynamics of the Sinkhorn algorithm in the regime of low entropy regularization
Derives the cold Sinkhorn limiting dynamics as tau approaches zero, proving finite-time convergence to unregularized OT and improved O(tau^{-1}) iteration complexity for dual suboptimality.
-
Sharp $O(1/k)$ convergence rate for the Sinkhorn algorithm via a local analysis
Proves sharp O(1/k) rate for Sinkhorn via local bipartite graph analysis of positive-mass edges, bootstrapped from prior almost-sharp global bound.
-
TimeLAVA: Learning-Agnostic Valuation for Time Series Data
TimeLAVA values time series segments by marginal contribution to minimizing distributional discrepancy using selective wavelet transforms and unbalanced optimal transport, without model training.
-
Sample complexity of unbalanced entropic OT
Proves finite-sample bounds for the optimal coupling in unbalanced entropic OT via compactness and strong convexity of a translation-invariant dual.
-
Spherical Harmonic Optimal Transport: Application to Climate Models Comparisons
Heat kernel Sinkhorn algorithm on the 2-sphere converges to OT cost with O(n) memory and O(n^{3/2}) time per iteration, retaining geometric properties and applied to climate model evaluation.
-
Debiasing optimal transport: classical and entropic
Debiasable ground costs lift to debiasable OT/EOT/MMD costs under negative-definiteness or continuous positive-semidefinite kernel conditions, via an inf-representation that also yields barycentric and interpolation formulas.
-
Multivariate Time Series Data Imputation via Distributionally Robust Regularization
DRIO adds worst-case Wasserstein regularization to time series imputation, yielding a tractable adversarial surrogate and alternating algorithm that improves robustness under missingness.
-
RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data
RECAST reconstructs black-box models under limited data by treating counterfactuals as class samples within a Wasserstein geometry framework to preserve surrogate fidelity without online access.