Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Rivaud, Stéphane"'
Autor:
Rivaud, Stéphane, Fournier, Louis, Pumir, Thomas, Belilovsky, Eugene, Eickenberg, Michael, Oyallon, Edouard
Reversible architectures have been shown to be capable of performing on par with their non-reversible architectures, being applied in deep learning for memory savings and generative modeling. In this work, we show how reversible architectures can sol
Externí odkaz:
http://arxiv.org/abs/2406.02052
Publikováno v:
Fortieth International Conference on Machine Learning, Jul 2023, Honolulu (Hawaii), USA, United States
Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient computati
Externí odkaz:
http://arxiv.org/abs/2306.06968
Autor:
Rivaud, Stephane, Pachet, François
We aim at enforcing hard constraints to impose a global structure on sequences generated from Markov models. In this report, we study the complexity of sampling Markov sequences under two classes of constraints: Binary Equalities and Grammar Membersh
Externí odkaz:
http://arxiv.org/abs/1711.10436