Publications related to Quantifying high-order interdependencies via multivariate extensions of the mutual information

Robust Generalization via $\alpha$-Mutual Information

Michael Christoph Gastpar, Amedeo Roberto Esposito, Ibrahim Issa

The aim of this work is to provide bounds connecting two probability measures of the same event using Rényi

\alpha

-Divergences and Sibson’s

\alpha

-Mutual Information, a generalization of respectively the Kullback-Leibler Divergence and Shannon’s Mutual ...

ETHZ2020

Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions

Anirudh Raju Natarajan

The free energy of a system is central to many material models. Although free energy data is not generally found directly, its derivatives can be observed or calculated. In this work, we present an Integrable Deep Neural Network (IDNN) that can be trained ...

Elsevier2019

Strengthened Information-theoretic Bounds on the Generalization Error

Michael Christoph Gastpar, Amedeo Roberto Esposito, Ibrahim Issa

The following problem is considered: given a joint distribution P XY and an event E, bound P XY (E) in terms of P X P Y (E) (where P X P Y is the product of the marginals of P XY ) and a measure of dependence of X and Y. Such bounds have direct application ...

IEEE2019

Statistical Physics Methods for Community Detection

Chun Lam Chan

This thesis is devoted to information-theoretic aspects of community detection. The importance of community detection is due to the massive amount of scientific data today that describes relationships between items from a network, e.g., a social network. I ...

EPFL2019

Mutual Information for the Stochastic Block Model by the Adaptive Interpolation Method

Nicolas Macris, Jean François Emmanuel Barbier, Chun Lam Chan

We rigorously derive a single-letter variational expression for the mutual information of the asymmetric two-groups stochastic block model in the dense graph regime. Existing proofs in the literature are indirect, as they involve mapping the model to a ran ...

IEEE2019

High-Dimensional Inference on Dense Graphs with Applications to Coding Theory and Machine Learning

Mohamad Baker Dia

We are living in the era of "Big Data", an era characterized by a voluminous amount of available data. Such amount is mainly due to the continuing advances in the computational capabilities for capturing, storing, transmitting and processing data. However, ...

EPFL2018

Unsupervised Change Detection in Satellite Images using Oversegmentation and Mutual Information

Bahar Taskesen, Beril Besbinar

In this paper, a novel solution to the problem of unsupervised change detection in bitemporal satellite images is presented. Information measures, which are well-known and commonly-used in the change detection literature, result in unsharp change maps and ...

Ieee2017

The Bethe Free Energy Allows to Compute the Conditional Entropy of Graphical Code Instances: A Proof From the Polymer Expansion

Nicolas Macris, Marc Vuffray

The main objective of this paper is to explore the precise relationship between the Bethe free energy (or entropy) and the Shannon conditional entropy of graphical error correcting codes. The main result shows that the Bethe free energy associated with a l ...

Ieee-Inst Electrical Electronics Engineers Inc2016

Statistical mechanics of wind wave-induced erosion in shallow tidal basins: Inferences from the Venice Lagoon

Andrea Rinaldo

Wind wave-induced erosional effects are among the chief landscape-forming processes in tidal biomorphodynamics. Wave-driven bottom erosion, in fact, controls the equilibrium elevation and dynamics of subtidal and tidal flat surfaces, and the impact of wave ...

American Geophysical Union2013

Efficient First-Principles Calculation of the Quantum Kinetic Energy and Momentum Distribution of Nuclei

Michele Ceriotti

Light nuclei at room temperature and below exhibit a kinetic energy which significantly deviates from the predictions of classical statistical mechanics. This quantum kinetic energy is responsible for a wide variety of isotope effects of interest in fields ...

2012

Quantifying high-order interdependencies via multivariate extensions of the mutual information

Graph Chatbot

Chat with Graph Search

Robust Generalization via $\alpha$-Mutual Information

Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions

Strengthened Information-theoretic Bounds on the Generalization Error

Statistical Physics Methods for Community Detection

Mutual Information for the Stochastic Block Model by the Adaptive Interpolation Method

High-Dimensional Inference on Dense Graphs with Applications to Coding Theory and Machine Learning

Unsupervised Change Detection in Satellite Images using Oversegmentation and Mutual Information

The Bethe Free Energy Allows to Compute the Conditional Entropy of Graphical Code Instances: A Proof From the Polymer Expansion

Statistical mechanics of wind wave-induced erosion in shallow tidal basins: Inferences from the Venice Lagoon

Efficient First-Principles Calculation of the Quantum Kinetic Energy and Momentum Distribution of Nuclei

Statistical Physics Methods for Community Detection

High-Dimensional Inference on Dense Graphs with Applications to Coding Theory and Machine Learning

Strengthened Information-theoretic Bounds on the Generalization Error

Statistical mechanics of wind wave-induced erosion in shallow tidal basins: Inferences from the Venice Lagoon

Efficient First-Principles Calculation of the Quantum Kinetic Energy and Momentum Distribution of Nuclei

Robust Generalization via $\alpha$-Mutual Information

Mutual Information for the Stochastic Block Model by the Adaptive Interpolation Method

Unsupervised Change Detection in Satellite Images using Oversegmentation and Mutual Information

The Bethe Free Energy Allows to Compute the Conditional Entropy of Graphical Code Instances: A Proof From the Polymer Expansion

Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions