A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
MB Khuzani, L Shen, S Shahrampour… - arXiv preprint arXiv …, 2019 - arxiv.org
We propose a novel supervised learning method to optimize the kernel in the maximum
mean discrepancy generative adversarial networks (MMD GANs), and the kernel support
vector machines (SVMs). Specifically, we characterize a distributionally robust optimization
problem to compute a good distribution for the random feature model of Rahimi and Recht.
Due to the fact that the distributional optimization is infinite dimensional, we consider a
Monte-Carlo sample average approximation (SAA) to obtain a more tractable finite …
mean discrepancy generative adversarial networks (MMD GANs), and the kernel support
vector machines (SVMs). Specifically, we characterize a distributionally robust optimization
problem to compute a good distribution for the random feature model of Rahimi and Recht.
Due to the fact that the distributional optimization is infinite dimensional, we consider a
Monte-Carlo sample average approximation (SAA) to obtain a more tractable finite …
A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
M Badiei Khuzani, L Shen, S Shahrampour… - arXiv e …, 2019 - ui.adsabs.harvard.edu
We propose a novel supervised learning method to optimize the kernel in the maximum
mean discrepancy generative adversarial networks (MMD GANs), and the kernel support
vector machines (SVMs). Specifically, we characterize a distributionally robust optimization
problem to compute a good distribution for the random feature model of Rahimi and Recht.
Due to the fact that the distributional optimization is infinite dimensional, we consider a
Monte-Carlo sample average approximation (SAA) to obtain a more tractable finite …
mean discrepancy generative adversarial networks (MMD GANs), and the kernel support
vector machines (SVMs). Specifically, we characterize a distributionally robust optimization
problem to compute a good distribution for the random feature model of Rahimi and Recht.
Due to the fact that the distributional optimization is infinite dimensional, we consider a
Monte-Carlo sample average approximation (SAA) to obtain a more tractable finite …
以上显示的是最相近的搜索结果。 查看全部搜索结果