Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory

no code implementations • NeurIPS 2023 • Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

Since their inception, Variational Autoencoders (VAEs) have become central in machine learning.

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

1 code implementation • 17 Feb 2023 • Sokhna Diarra Mbacke, Florence Clerc, Pascal Germain

We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the total variation distance.

Dimensionality Reduction Generalization Bounds