stat.MLNov 13, 2026

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

Authors: Eduardo Pinto, Panagiota Birmpa

Organizations: Instituto Superior Técnico, Department of Mathematics, University of Lisbon · Department of Actuarial Mathematics and Statistics, Heriot-Watt University and the Maxwell Institute for Mathematical Sciences

Abstract

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

Figures & tables

Explore similar work

CardsList
  1. Seasoning Generative Models for a Generalization Aftertaste

    Mar 19, 2026Hisham Husain, Valentin De Bortoli, Richard NockGenerative ModelingGeneralization Bounds

  2. Revisiting GAN with Bayes-Optimal Discrimination

    Oct 29, 2025Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad +2TV Distance ComputationGenerative Adversarial Networks

  3. A Distribution-Matching Perspective on LLM Training Algorithms

    Oct 24, 2026Yanxing Huang, Bingzhang Yan, Zihan Tang +3LLM TrainingLanguage Model Distillation