4 citations · 7 across the 3 of their papers we have counts for
5 papers
One Reflection Suffice
Alexander Mathiasen, Frederik Hvilshøj
Orthogonal weight matrices are used in many areas of deep learning. Much previous work attempt to alleviate the additional computational resources it requires to constrain weight m…
What if Neural Networks had SVDs?
Alexander Mathiasen, Frederik Hvilshøj, Jakob Rødsgaard Jørgensen +2
Various Neural Networks employ time-consuming matrix operations like matrix inversion. Many such matrix operations are faster to compute given the Singular Value Decomposition (SVD…
Backpropagating through Fréchet Inception Distance
Alexander Mathiasen, Frederik Hvilshøj
The Fréchet Inception Distance (FID) has been used to evaluate hundreds of generative models. We introduce FastFID, which can efficiently train generative models with FID as a loss…
Margin-Based Generalization Lower Bounds for Boosted Classifiers
Allan Grønlund, Lior Kamma, Kasper Green Larsen +2
Boosting is one of the most successful ideas in machine learning. The most well-accepted explanations for the low generalization error of boosting algorithms such as AdaBoost stem…
Optimal Minimal Margin Maximization with Boosting
Allan Grønlund, Kasper Green Larsen, Alexander Mathiasen
Boosting algorithms produce a classifier by iteratively combining base hypotheses. It has been observed experimentally that the generalization error keeps improving even after achi…