2 citations · 2 across the 1 of their papers we have counts for
4 papers
Zuckerli: A New Compressed Representation for Graphs
Luca Versari, Iulia M. Comsa, Alessio Conte +1
Zuckerli is a scalable compression system meant for large real-world graphs. Graphs are notoriously challenging structures to store efficiently due to their linked nature, which ma…
Intelligent Matrix Exponentiation
Thomas Fischbacher, Iulia M. Comsa, Krzysztof Potempa +3
We present a novel machine learning architecture that uses the exponential of a single input-dependent matrix as its only nonlinearity. The mathematical simplicity of this architec…
Committee Draft of JPEG XL Image Coding System
Alexander Rhatushnyak, Jan Wassenberg, Jon Sneyers +15
JPEG XL is a practical approach focused on scalable web distribution and efficient compression of high-quality images. It provides various benefits compared to existing image forma…
SO(8) Supergravity and the Magic of Machine Learning
Iulia M. Comsa, Moritz Firsching, Thomas Fischbacher
Using de Wit-Nicolai supergravity as an example, we show how modern Machine Learning software libraries such as Google's TensorFlow can be employed to g…