English

Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution

Statistics Theory 2024-06-07 v2 Machine Learning Machine Learning Statistics Theory

Abstract

This paper explores the problem of generative modeling, aiming to simulate diverse examples from an unknown distribution based on observed examples. While recent studies have focused on quantifying the statistical precision of popular algorithms, there is a lack of mathematical evaluation regarding the non-replication of observed examples and the creativity of the generative model. We present theoretical insights into this aspect, demonstrating that the Wasserstein GAN, constrained to left-invertible push-forward maps, generates distributions that avoid replication and significantly deviate from the empirical distribution. Importantly, we show that left-invertibility achieves this without compromising the statistical optimality of the resulting generator. Our most important contribution provides a finite-sample lower bound on the Wasserstein-1 distance between the generative distribution and the empirical one. We also establish a finite-sample upper bound on the distance between the generative distribution and the true data-generating one. Both bounds are explicit and show the impact of key parameters such as sample size, dimensions of the ambient and latent spaces, noise level, and smoothness measured by the Lipschitz constant.

Keywords

Cite

@article{arxiv.2307.16422,
  title  = {Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution},
  author = {Elen Vardanyan and Sona Hunanyan and Tigran Galstyan and Arshak Minasyan and Arnak Dalalyan},
  journal= {arXiv preprint arXiv:2307.16422},
  year   = {2024}
}

Comments

ICML 2024

R2 v1 2026-06-28T11:44:05.605Z