Zobrazeno 1 - 6
of 6
pro vyhledávání: '"68T07, 49Q22"'
Autor:
Rodriguez, Pau, Blaas, Arno, Klein, Michal, Zappella, Luca, Apostoloff, Nicholas, Cuturi, Marco, Suau, Xavier
The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control model generati
Externí odkaz:
http://arxiv.org/abs/2410.23054
Several problems in stochastic analysis are defined through their geometry, and preserving that geometric structure is essential to generating meaningful predictions. Nevertheless, how to design principled deep learning (DL) models capable of encodin
Externí odkaz:
http://arxiv.org/abs/2201.13094
We propose two deep neural network-based methods for solving semi-martingale optimal transport problems. The first method is based on a relaxation/penalization of the terminal constraint, and is solved using deep neural networks. The second method is
Externí odkaz:
http://arxiv.org/abs/2103.03628
On the Convergence of Gradient Descent Training for Two-layer ReLU-networks in the Mean Field Regime
Autor:
Wojtowytsch, Stephan
We describe a necessary and sufficient condition for the convergence to minimum Bayes risk when training two-layer ReLU-networks by gradient descent in the mean field regime with omni-directional initial parameter distribution. This article extends r
Externí odkaz:
http://arxiv.org/abs/2005.13530
Autor:
Wojtowytsch, Stephan, E, Weinan
We prove that the gradient descent training of a two-layer neural network on empirical or population risk may not decrease population risk at an order faster than $t^{-4/(d-2)}$ under mean field scaling. Thus gradient descent training for fitting rea
Externí odkaz:
http://arxiv.org/abs/2005.10815
Publikováno v:
Mathematical Finance
Several problems in stochastic analysis are defined through their geometry, and preserving that geometric structure is essential to generating meaningful predictions. Nevertheless, how to design principled deep learning (DL) models capable of encodin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dea789c5ae2fb5e916243750ac5ec5f7
http://arxiv.org/abs/2201.13094
http://arxiv.org/abs/2201.13094