One Reflection Suffice

no code implementations • 30 Sep 2020 • Alexander Mathiasen, Frederik Hvilshøj

Orthogonal weight matrices are used in many areas of deep learning.

What if Neural Networks had SVDs?

1 code implementation • NeurIPS 2020 • Alexander Mathiasen, Frederik Hvilshøj, Jakob Rødsgaard Jørgensen, Anshul Nasery, Davide Mottin

We present an algorithm that is fast enough to speed up several matrix operations.

Backpropagating through Fréchet Inception Distance

no code implementations • 29 Sep 2020 • Alexander Mathiasen, Frederik Hvilshøj

Using FID as an additional loss for Generative Adversarial Networks improves their FID.

Margin-Based Generalization Lower Bounds for Boosted Classifiers

no code implementations • NeurIPS 2019 • Allan Grønlund, Lior Kamma, Kasper Green Larsen, Alexander Mathiasen, Jelani Nelson

To date, the strongest known generalization (upper bound) is the $k$th margin bound of Gao and Zhou (2013).

Generalization Bounds

Optimal Minimal Margin Maximization with Boosting

no code implementations • 30 Jan 2019 • Allan Grønlund, Kasper Green Larsen, Alexander Mathiasen

A common goal in a long line of research, is to maximize the smallest margin using as few base hypotheses as possible, culminating with the AdaBoostV algorithm by (R{\"a}tsch and Warmuth [JMLR'04]).

Fast Exact k-Means, k-Medians and Bregman Divergence Clustering in 1D

1 code implementation • 25 Jan 2017 • Allan Grønlund, Kasper Green Larsen, Alexander Mathiasen, Jesper Sindahl Nielsen, Stefan Schneider, Mingzhou Song

We present all the existing work that had been overlooked and compare the various solutions theoretically.