Français
Generalisation of some overparametrised models
Multi angle
Authors : Chrétien, Stéphane (Author of the conference)
CIRM (Publisher )
68T05 - Learning and adaptive systems
Additional resources :
https://www.cirm-math.fr/RepOrga/2551/Slides/CHRETIEN.pdf
CIRM (Publisher )
Loading the player...
|
Abstract :
The statistical problem of estimating a Sobolev function using a deep network is studied using the Neuberger theorem and recent approximation results by Gurhing Kutyniok and Petersen. The problem is addressed by decoupling the statistical and the approximation problems and is shown to boil down to the computation of the Sobolev norm of bump functions.
Keywords : deep learning; generalisation; Sobolev spaces
MSC Codes : Keywords : deep learning; generalisation; Sobolev spaces
68T05 - Learning and adaptive systems
Additional resources :
https://www.cirm-math.fr/RepOrga/2551/Slides/CHRETIEN.pdf
|
Information on the Video
Film maker : Hennenfent, GuillaumeLanguage : English Available date : 10/11/2022 Conference Date : 04/10/2022 Subseries : Research talks arXiv category : Machine Learning Mathematical Area(s) : Mathematics in Science & Technology ; Probability & Statistics Format : MP4 (.mp4) - HD Video Time : 00:35:00 Targeted Audience : Researchers ; Graduate Students ; Doctoral Students, Post-Doctoral Students Download : https://videos.cirm-math.fr/2022-10-04_Chretien.mp4 
|
Information on the Event
Event Title : Learning and Optimization in Luminy - LOL2022 / Apprentissage et Optimisation à Luminy - LOL2022Event Organizers : Boyer, Claire ; d'Aspremont, Alexandre ; Dieuleveut, Aymeric ; Moreau, Thomas ; Villar, Soledad Dates : 03/10/2022 - 07/10/2022 Event Year : 2022 Event URL : https://conferences.cirm-math.fr/2551.html
Citation Data
DOI : 10.24350/CIRM.V.19965503Cite this video as: Chrétien, Stéphane (2022). Generalisation of some overparametrised models. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19965503 URI : http://dx.doi.org/10.24350/CIRM.V.19965503 |
See Also
- [Multi angle] Stochastic normalizing flows and the power of patches in inverse problems / Author of the conference Steidl, Gabriele.
- [Multi angle] Curiosities and counterexamples in smooth convex optimization / Author of the conference Pauwels, Edouard.
- [Multi angle] Private frequency estimation via projective geometry / Author of the conference Nelson, Jelani.
- [Multi angle] Non-convex SGD and Lojasiewicz-type conditions for deep learning / Author of the conference Scaman, Kevin.
Bibliography
Imagette Video
