133 citations · 141 across the 10 of their papers we have counts for
15 papers
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…
PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images
Simon Damm, Jonas Ricker, Henning Petzka +1
Autoregressive (AR) image generation has recently emerged as a powerful paradigm for image synthesis. Leveraging the generation principle of large language models, they allow for e…
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…
On the regularization of Wasserstein GANs
Henning Petzka, Asja Fischer, Denis Lukovnikov
Since their invention, generative adversarial networks (GANs) have become a popular approach for learning to model a distribution of real (unlabeled) data. Convergence problems dur…
Perforation conditions and almost algebraic order in Cuntz semigroups
Ramon Antoine, Francesc Perera, Henning Petzka
For a C-algebra , it is an important problem to determine the Cuntz semigroup in terms of . We approach this problem from…
Comparison Properties of the Cuntz semigroup and applications to C*-algebras
Joan Bosa, Henning Petzka
We study comparison properties in the category Cu aiming to lift results to the C*-algebraic setting. We introduce a new comparison property and relate it to both the CFP and -c…
Corrigendum to "Regularity for stably projectionless, simple C*-algebras"
Henning Petzka, Aaron Tikuisis
An error is identified and corrected in the construction of a non-Z-stable, stably projectionless, simple, nuclear C*-algebra carried out in a paper by the second author.
Geometric Structure of Dimension Functions of Certain Continuous Fields
Ramon Antoine, Joan Bosa, Francesc Perera +1
In this paper we study structural properties of the Cuntz semigroup and its functionals for continuous fields of C*-algebras over finite dimensional spaces. In a variety of cases,…
The Blackadar-Handelman theorem for non-unital C*-algebras
Henning Petzka
A well-known theorem of Blackadar and Handelman states that every unital stably finite C*-algebra has a bounded quasitrace. Rather strong generalizations of stable finiteness to th…
On certain multiplier projections
Henning Petzka
Let $\MCZK$, denote the multiplier algebra over $\CZK$, the algebra of continuous functions into the compact operators with spectrum the infinite product of two-spheres. We conside…