We refine a recently-proposed class of local entropic loss functions by restricting the smoothening regularization to only subset weights. The new are referred as partial entropies. They can adapt weight-space anisotropy, thus outperforming their isotropic counterparts. support theoretical analysis with experiments on image classification tasks performed multi-layer, fully-connected and convolu...

A quantitative connection between correlation functions and entanglement is established. In particular, the zeros of local matrices are shown to give an upper bound on entropy.

Potentially influential spaces in the spatial networks of cities can be detected by means of the entropy participation ratios. Local (connectivity) and global (centrality) entropies are considered. While the connectivity entropy has a tendency to increase with the city size, the centrality entropy is decreasing that reflects the global connectedness of cities. In urban networks , the local and ...

in this paper we introduce the concept of entropy operator for continuous systems of finite topological entropy. it is shown that it generates the kolmogorov entropy as a special case. if $phi$ is invertible then the entropy operator is bounded with the topological entropy of $phi$ as its norm.

In this letter, we connect some recent papers on smoothing of energy landscapes and scored-based generative models machine learning to classical work in stochastic control. We clarify these connections providing rigorous statements representations which may serve as guidelines for further models.