4 papers
The Latent Information Geometry of Jet Classification
Rebecca Maria Kuntz, Tilman Plehn, Björn Malte Schäfer +2
Latent representations are an important theme in modern machine learning. Any network training with the notion of locality introduces a latent geometry which we can analyze with th…
Rényi-Induced Information Geometry and Hartigan's Prior Family
Rebecca Maria Kuntz, Heinrich von Campe, Björn Malte Schäfer
We derive the information geometry induced by the statistical Rényi divergence, namely its metric tensor, its dual parametrized connections, as well as its dual Laplacians. Based…
Partition function approach to non-Gaussian likelihoods: information theory and state variables for Bayesian inference
Rebecca Maria Kuntz, Heinrich von Campe, Tobias Röspel +2
The significance of statistical physics concepts such as entropy extends far beyond classical thermodynamics. We interpret the similarity between partitions in statistical mechanic…
Partition function approach to non-Gaussian likelihoods: macrocanonical partitions and replicating Markov-chains
Maximilian Philipp Herzog, Heinrich von Campe, Rebecca Maria Kuntz +2
Monte-Carlo techniques are standard numerical tools for exploring non-Gaussian and multivariate likelihoods. Many variants of the original Metropolis-Hastings algorithm have been p…