Florence Clerc

Prakash Panangaden

2023-12-27

ArXiv (prépublication)

arxiv.org

Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory

Sokhna Diarra Mbacke

Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory

Sokhna Diarra Mbacke

2023-09-21

NeurIPS.cc/2023/Conference (spotlight)

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

Sokhna Diarra Mbacke

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (publié)

Behavioural equivalences for continuous-time Markov processes

Linan Chen

Prakash Panangaden

2023-03-30

Mathematical Structures in Computer Science (publié)

PAC-Bayesian Generalization Bounds for Adversarial Generative Models

Sokhna Diarra Mbacke

We extend PAC-Bayesian theory to generative models and develop generalization bounds for models based on the Wasserstein distance and the to… (voir plus)tal variation distance. Our first result on the Wasserstein distance assumes the instance space is bounded, while our second result takes advantage of dimensionality reduction. Our results naturally apply to Wasserstein GANs and Energy-Based GANs, and our bounds provide new training objectives for these two. Although our work is mainly theoretical, we perform numerical experiments showing non-vacuous generalization bounds for Wasserstein GANs on synthetic datasets.

2023-01-01

ICML (publié)

Sample Boosting Algorithm (SamBA) - An interpretable greedy ensemble classifier based on local expertise for fat data

Baptiste Bauvin

Cécile Capponi