pith. the verified trust layer for science. sign in

arxiv: 1810.08278 · v1 · pith:FSGPDUZQnew · submitted 2018-10-18 · 🧮 math.ST · stat.TH

Interpolating between Optimal Transport and MMD using Sinkhorn Divergences

classification 🧮 math.ST stat.TH
keywords divergencesgeometricsinkhornconvergencedistancesentropyoptimalproblem
0
0 comments X p. Extension
Add this Pith Number to your LaTeX paper What is a Pith Number?
\usepackage{pith}
\pithnumber{FSGPDUZQ}

Prints a linked pith:FSGPDUZQ badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

Comparing probability distributions is a fundamental problem in data sciences. Simple norms and divergences such as the total variation and the relative entropy only compare densities in a point-wise manner and fail to capture the geometric nature of the problem. In sharp contrast, Maximum Mean Discrepancies (MMD) and Optimal Transport distances (OT) are two classes of distances between measures that take into account the geometry of the underlying space and metrize the convergence in law. This paper studies the Sinkhorn divergences, a family of geometric divergences that interpolates between MMD and OT. Relying on a new notion of geometric entropy, we provide theoretical guarantees for these divergences: positivity, convexity and metrization of the convergence in law. On the practical side, we detail a numerical scheme that enables the large scale application of these divergences for machine learning: on the GPU, gradients of the Sinkhorn loss can be computed for batches of a million samples.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. On Model-Based Clustering With Entropic Optimal Transport

    stat.ME 2026-05 unverdicted novelty 6.0

    Entropic optimal transport yields a clustering loss with the same global optimum as log-likelihood but a better-behaved optimization surface, outperforming standard EM in experiments.

  2. One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization

    cs.SD 2026-01 unverdicted novelty 6.0

    LLMs using in-context learning and fine-tuning on listener experiment data generate equalization settings that align better with population preferences than random sampling or static presets.