133 citations · 141 across the 10 of their papers we have counts for
7 papers · 1 filter
Geometric and Information Compression of Representations in Deep Learning
Linara Adilova, Henning Petzka, Asja Fischer +1
Deep neural networks transform input data into latent representations that support a wide range of downstream tasks. These representations can be characterized along information-th…
Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking
Ting Han, Linara Adilova, Henning Petzka +2
Neural collapse, i.e., the emergence of highly symmetric, class-wise clustered representations, is frequently observed in deep networks and is often assumed to reflect or enable ge…
FAM: Relative Flatness Aware Minimization
Linara Adilova, Amr Abourayya, Jianning Li +5
Flatness of the loss curve around a model at hand has been shown to empirically correlate with its generalization ability. Optimizing for flatness has been proposed as early as 199…
Discriminating Against Unrealistic Interpolations in Generative Adversarial Networks
Henning Petzka, Ted Kronvall, Cristian Sminchisescu
Interpolations in the latent space of deep generative models is one of the standard tools to synthesize semantically meaningful mixtures of generated samples. As the generator func…
Relative Flatness and Generalization
Henning Petzka, Michael Kamp, Linara Adilova +2
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks. While it has been empirically obs…
A Reparameterization-Invariant Flatness Measure for Deep Neural Networks
Henning Petzka, Linara Adilova, Michael Kamp +1
The performance of deep neural networks is often attributed to their automated, task-related feature construction. It remains an open question, though, why this leads to solutions…
Non-attracting Regions of Local Minima in Deep and Wide Neural Networks
Henning Petzka, Cristian Sminchisescu
Understanding the loss surface of neural networks is essential for the design of models with predictable performance and their success in applications. Experimental results suggest…