REVIEW 5 cited by
Sinkhorn Divergences for Unbalanced Optimal Transport
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Optimal transport induces the Earth Mover's (Wasserstein) distance between probability distributions, a geometric divergence that is relevant to a wide range of problems. Over the last decade, two relaxations of optimal transport have been studied in depth: unbalanced transport, which is robust to the presence of outliers and can be used when distributions don't have the same total mass; entropy-regularized transport, which is robust to sampling noise and lends itself to fast computations using the Sinkhorn algorithm. This paper combines both lines of work to put robust optimal transport on solid ground. Our main contribution is a generalization of the Sinkhorn algorithm to unbalanced transport: our method alternates between the standard Sinkhorn updates and the pointwise application of a contractive function. This implies that entropic transport solvers on grid images, point clouds and sampled distributions can all be modified easily to support unbalanced transport, with a proof of linear convergence that holds in all settings. We then show how to use this method to define pseudo-distances on the full space of positive measures that satisfy key geometric axioms: (unbalanced) Sinkhorn divergences are differentiable, positive, definite, convex, statistically robust and avoid any "entropic bias" towards a shrinkage of the measures' supports.
Forward citations
Cited by 5 Pith papers
-
Sharp Convergence Rates of Empirical Unbalanced Optimal Transport for Spatio-Temporal Point Processes
For weakly time-stationary spatio-temporal point processes with sub-quadratic variance growth, the empirical Kantorovich-Rubinstein distance converges at rates matching classical Wasserstein rates in intrinsic dimensi...
-
Symmetrized Sinkhorn-Gibbs Inference for Oscillatory Inverse Problems
A symmetrized Sinkhorn divergence, averaging transport costs of a signal and its negation, yields better Gibbs posterior inference for oscillatory inverse problems.
-
Distributional Determinantal Point Process for Repulsive Clustering of Distributions
A dDPP prior built on a sliced Wasserstein kernel provides a repulsive distribution-valued point process that, in a generalized Bayesian mixture model, clusters distributions into better-separated groups than a Dirich...
-
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.
-
Distributionally Robust Shape and Topology Optimization
The paper derives tractable single-level reformulations of distributionally robust shape and topology optimization for Wasserstein, moment, and CVaR ambiguity sets, and demonstrates them numerically.
Discussion (0). Sign in to comment.