Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
On the Convergence Rate of S inkhorn’s Algorithm
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
PINS combines an outer proximal-point loop over shifted entropic OT problems with inner Sinkhorn warm-up and sparse-Newton refinement to reach unregularized OT solutions with global convergence and lower error than Sinkhorn baselines.
Establishes the first non-asymptotic exponential convergence rates for Sinkhorn's algorithm on unbounded quadratic costs with non-compact marginals satisfying asymptotically positive log-concavity.
citing papers explorer
-
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
-
PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
PINS combines an outer proximal-point loop over shifted entropic OT problems with inner Sinkhorn warm-up and sparse-Newton refinement to reach unregularized OT solutions with global convergence and lower error than Sinkhorn baselines.
-
Quantitative contraction rates for Sinkhorn's algorithm: beyond bounded costs and compact marginals
Establishes the first non-asymptotic exponential convergence rates for Sinkhorn's algorithm on unbounded quadratic costs with non-compact marginals satisfying asymptotically positive log-concavity.