Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Cédric Gerbelot"'
Autor:
Elisabetta Cornacchia, Francesca Mignacco, Rodrigo Veiga, Cédric Gerbelot, Bruno Loureiro, Lenka Zdeborová
Publikováno v:
Machine Learning: Science and Technology, Vol 4, Iss 1, p 015019 (2023)
One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with a single-layer teacher–student perceptron on i.i.d. Gaussian inputs. Both Bayes-optim
Externí odkaz:
https://doaj.org/article/0e933c7c1af445c798d726f853b9ee0a
Autor:
Paul Fowler, Elie Raphaël, Kari Dalnoki-Veress, Michael Benzaquen, Miles Couchman, Howard A. Stone, Cédric Gerbelot, Thomas Salez, Mark Ilton
Publikováno v:
Physical Review Letters
Physical Review Letters, American Physical Society, 2016, 117 (16), ⟨10.1103/PhysRevLett.117.167801⟩
Physical Review Letters, American Physical Society, 2016, 117 (16), ⟨10.1103/PhysRevLett.117.167801⟩
We report on the capillary-driven levelling of a topographical perturbation at the surface of a free-standing liquid nanofilm. The width of a stepped surface profile is found to evolve as the square root of time. The hydrodynamic model is in excellen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::669c03dd78f03070728a7a6672d2f0b1
http://arxiv.org/abs/1602.05538
http://arxiv.org/abs/1602.05538
Autor:
Bruno Loureiro, Gabriele Sicuro, Cédric Gerbelot, Alessandro Pacco, Florent Krzakala, Lenka Zdeborová
Publikováno v:
King's College London
Generalised linear models for multi-class classification problems are one of the fundamental building blocks of modern machine learning tasks. In this manuscript, we characterise the learning of a mixture of K Gaussians with generic means and covaria
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::0aa5767b834490be2d5a5d24b1a0c292
https://kclpure.kcl.ac.uk/portal/en/publications/learning-gaussian-mixtures-with-generalized-linear-models-precise-asymptotics-in-highdimensions(750b36ae-bc9a-4bb8-9aaa-f1a1f4f017c4).html
https://kclpure.kcl.ac.uk/portal/en/publications/learning-gaussian-mixtures-with-generalized-linear-models-precise-asymptotics-in-highdimensions(750b36ae-bc9a-4bb8-9aaa-f1a1f4f017c4).html
Autor:
Elisabetta Cornacchia, Francesca Mignacco, Rodrigo Veiga, Cédric Gerbelot, Bruno Loureiro, Lenka Zdeborová
One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with the single-layer teacher-student perceptron on i.i.d. Gaussian inputs. Both Bayes-optim
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3930f2e0a26707589b3cc8a267bc79a9
https://infoscience.epfl.ch/record/301053
https://infoscience.epfl.ch/record/301053