Výsledky vyhledávání

On PAC-Bayesian reconstruction guarantees for VAEs

Autor: Cherief-Abdellatif, B-E, Shi, Y, Doucet, A, Guedj, B

Publikováno v: 25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022
25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022, Mar 2022, Valencia / Virtual, Spain

Despite its wide use and empirical successes, the theoretical understanding and study of the behaviour and performance of the variational autoencoder (VAE) have only emerged in the past few years. We contribute to this recent line of work by analysin

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a65937a9f0aa496bb191e622e21cbfd6
https://inria.hal.science/hal-03587178

Zobrazit plný text záznamu

Online k-means clustering

Autor: Cohen-Addad, V, Guedj, B, Rom, G

We study the problem of learning a clustering of an online set of points. The specific formulation we use is the k-means objective: At each time step the algorithm has to maintain a set of k candidate centers and the loss incurred by the algorithm is

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______1064::18762a2a9a8766707a266d2d54fb1b41
https://ora.ox.ac.uk/objects/uuid:2dc0ce88-fc92-4ef6-9ee1-8bc8c3184620

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Dichotomize and Generalize:PAC-Bayesian Binary Activated Deep Neural Networks

Autor: Letarte, G. (Gaël), Germain, P. (Pascal), Guedj, B. (Benjamin), Laviolette, F. (François)

We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory. Our contributions are twofold: (i) we develop an end-to-end framework to train a binary activated deep neural network, overcomi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______4198::3611ae88290cc1831d2baed4f77102ef
http://hdl.handle.net/20.500.12210/29179

Zobrazit plný text záznamu

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks

Autor: Letarte, G., Guedj, B., Pascal Germain, Laviolette, F.

Publikováno v: NeurIPS 2019-Thirty-third Conference on Neural Information Processing Systems
NeurIPS 2019-Thirty-third Conference on Neural Information Processing Systems, Dec 2019, Vancouver, Canada
ML with guarantees--NeurIPS 2019 workshop
ML with guarantees--NeurIPS 2019 workshop, Dec 2019, Vancouver, Canada
Scopus-Elsevier

International audience; We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory. Our contributions are twofold: (i) we develop an end-to-end framework to train a binary activated deep

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be212b483192a82465a499e0d273dfab
https://hal.inria.fr/hal-02139432v2/document

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání