Newshot

Lipschitz-Constrained Discriminators in Generative Modeling: Asymptotic Behavior and Support Mismatch

Summary

arXiv:2611.18394v1 Announce Type: new Abstract: We study the asymptotic behavior of optimal discriminators associated to $L-$Lipschitz regularized KL-divergences of two probability distributions $Q$ and $P$ that interpolate between the rescaled Wasserstein$-1$ metric by some parameter $L>0$ and the KL divergence. The parameter $L$ plays the role of a Lipschitz constraint and is viewed as a regularization parameter: small values of $L$ enforce a more geometry-aware discriminator, while as $L$ increases the geometric regularization is progressively relaxed. It is a known result [3] that such divergences converge to the KL divergence as $L\to\infty$. In this paper, we characterize the asymptotic behavior of the optimal discriminators as $L\to\infty$ in different regimes: Firstly, under $Q\ll P$ and the Radon-Nikodym derivative $\frac{dQ}{dP}$ is bounded from above and bounded away from zero. Secondly, when $Q$ and $P$ are discrete distributions satisfying $Q\ll P$, and finally when $Q$ an…

Original text(via arXiv stat.ML)

Statistics > Machine Learning

Title:Lipschitz-Constrained Discriminators in Generative Modeling: Asymptotic Behavior and Support Mismatch

Abstract:We study the asymptotic behavior of optimal discriminators associated to $L-$Lipschitz regularized KL-divergences of two probability distributions $Q$ and $P$ that interpolate between the rescaled Wasserstein$-1$ metric by some parameter $L>0$ and the KL divergence. The parameter $L$ plays the role of a Lipschitz constraint and is viewed as a regularization parameter: small values of $L$ enforce a more geometry-aware discriminator, while as $L$ increases the geometric regularization is progressively relaxed. It is a known result [3] that such divergences converge to the KL divergence as $L\to\infty$. In this paper, we characterize the asymptotic behavior of the optimal discriminators as $L\to\infty$ in different regimes: Firstly, under $Q\ll P$ and the Radon-Nikodym derivative $\frac{dQ}{dP}$ is bounded from above and bounded away from zero. Secondly, when $Q$ and $P$ are discrete distributions satisfying $Q\ll P$, and finally when $Q$ and $P$ are non absolutely continuous discrete distributions. This result motivates training strategies which involve discriminators, such as adversarial generative models. In practice, the data distribution is often represented by a discrete empirical measure, while, especially at the early stages of the training, the model distribution may have little or no overlap with the empirical data distribution.
Subjects:Machine Learning (stat.ML) ; Machine Learning (cs.LG)
MSC classes:49J45, 94A17, 62B10
Cite as:arXiv:2611.18394 [stat.ML]
(or arXiv:2611.18394v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2611.18394 arXiv-issued DOI via DataCite (pending registration)

Submission history

Access Paper:

  • HTML (experimental)

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv stat.ML
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗