Zobrazeno 1 - 10
of 188
pro vyhledávání: '"Aurelie, C."'
We study the training of regularized neural networks where the regularizer can be non-smooth and non-convex. We propose a unified framework for stochastic proximal gradient descent, which we term ProxGen, that allows for arbitrary positive preconditi
Externí odkaz:
http://arxiv.org/abs/2007.07484
Recent theoretical works based on the neural tangent kernel (NTK) have shed light on the optimization and generalization of over-parameterized networks, and partially bridge the gap between their practical success and classical learning theory. Espec
Externí odkaz:
http://arxiv.org/abs/2007.00884
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class of algorithms includes Adagrad, RMSprop, Adam, and recent extensions. All these algorit
Externí odkaz:
http://arxiv.org/abs/1905.10757
Autor:
Yu, Ming, Thompson, Addie M., Ramamurthy, Karthikeyan Natesan, Yang, Eunho, Lozano, Aurélie C.
Inferring predictive maps between multiple input and multiple output variables or tasks has innumerable applications in data science. Multi-task learning attempts to learn the maps to several output tasks simultaneously with information sharing betwe
Externí odkaz:
http://arxiv.org/abs/1710.01788
Sparse mapping has been a key methodology in many high-dimensional scientific problems. When multiple tasks share the set of relevant features, learning them jointly in a group drastically improves the quality of relevant feature selection. However,
Externí odkaz:
http://arxiv.org/abs/1705.04886
Autor:
Naidoo, Robin, Brennan, Angela, Shapiro, Aurelie C., Beytell, Piet, Aschenborn, Ortwin, Du Preez, Pierre, Kilian, J. Werner, Stuart-Hill, Greg, Taylor, Russell D.
Publikováno v:
Ecological Applications, 2020 Dec 01. 30(8), 1-12.
Externí odkaz:
https://www.jstor.org/stable/27029126
We consider the problem of removing and replacing clouds in satellite image sequences, which has a wide range of applications in remote sensing. Our approach first detects and removes the cloud-contaminated part of the image sequences. It then recove
Externí odkaz:
http://arxiv.org/abs/1604.03915
Autor:
Ashrafi, Hedieh, Thiele, Aurélie C.
Publikováno v:
In Operations Research Perspectives 2021 8
Autor:
Yang, Eunho, Lozano, Aurélie C.
Gaussian Graphical Models (GGMs) are popular tools for studying network structures. However, many modern applications such as gene network discovery and social interactions analysis often involve high-dimensional noisy data with outliers or heavier t
Externí odkaz:
http://arxiv.org/abs/1510.08512