Search Results for author:
Found 8 papers, 4 papers with code
FAM: Relative Flatness Aware Minimization
Their widespread adoption in practice, though, is dubious because of the lack of theoretically grounded connection between flatness and generalization, in particular in light of the reparameterization curse - certain reparameterizations of a neural network change most flatness measures but do not change generalization.
Discriminating Against Unrealistic Interpolations in Generative Adversarial Networks
By reusing the discriminator network to modify the metric on the latent space, we propose a lightweight solution for improved interpolations in pre-trained GANs.
TropEx: An Algorithm for Extracting Linear Terms in Deep Neural Networks
Deep neural networks with rectified linear (ReLU) activations are piecewise linear functions, where hyperplanes partition the input space into an astronomically high number of linear regions.
Relative Flatness and Generalization
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks.
A Reparameterization-Invariant Flatness Measure for Deep Neural Networks
The performance of deep neural networks is often attributed to their automated, task-related feature construction.
Feature-Robustness, Flatness and Generalization Error for Deep Neural Networks
With this, the generalization error of a model trained on representative data can be bounded by its feature robustness which depends on our novel flatness measure.
Non-attracting Regions of Local Minima in Deep and Wide Neural Networks
For extremely wide neural networks of decreasing width after the wide layer, we prove that every suboptimal local minimum belongs to such a connected set.
On the regularization of Wasserstein GANs
Since their invention, generative adversarial networks (GANs) have become a popular approach for learning to model a distribution of real (unlabeled) data.
