Publications related to A Wasserstein-based measure of conditional dependence

Geometrically-Conditioned Point Diffusion Models

Pascal Fua, Eduard Trulls Fortuny, Michal Jan Tyszkiewicz

Diffusion models generating images conditionally on text, such as Dall-E 2 [51] and Stable Diffusion[53], have recently made a splash far beyond the computer vision com- munity. Here, we tackle the related problem of generating point clouds, both unconditi ...

2023

The Gray-Wyner Network and Wyner's Common Information for Gaussian Sources

Michael Christoph Gastpar, Erixhen Sula

This paper presents explicit solutions for two related non-convex information extremization problems due to Gray and Wyner in the Gaussian case. The first problem is the Gray-Wyner network subject to a sum-rate constraint on the two private links. Here, ou ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Quantifying uncertain system outputs via the multi-level Monte Carlo method --- distribution and robustness measures

Fabio Nobile, Sebastian Krumscheid, Sundar Subramaniam Ganesh

In this work, we consider the problem of estimating the probability distribution, the quantile or the conditional expectation above the quantile, the so called conditional-value-at-risk, of output quantities of complex random differential models by the MLM ...

2022

Learning Constrained Distributions of Robot Configurations with Generative Adversarial Network

Sylvain Calinon, Julius Maximilian Jankowski, Emmanuel Pignat, Teguh Santoso Lembono

In high dimensional robotic system, the manifold of the valid configuration space often has a complex shape, especially under constraints such as end-effector orientation or static stability. We propose a generative adversarial network approach to learn th ...

IEEE2021

Distributionally Robust Optimization with Polynomial Densities: Theory, Models and Algorithms

Daniel Kuhn

In distributionally robust optimization the probability distribution of the uncertain problem parameters is itself uncertain, and a fictitious adversary, e.g., nature, chooses the worst distribution from within a known ambiguity set. A common shortcoming o ...

2020

On quantifying the quality of acoustic models in hybrid DNN-HMM ASR

Hervé Bourlard, Afsaneh Asaei, Pranay Dighe

We propose an information theoretic framework for quantitative assessment of acoustic models used in hidden Markov model (HMM) based automatic speech recognition (ASR). The HMM backend expects that (i) the acoustic model yields accurate state conditional e ...

ELSEVIER2020

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

Extremal behaviour of aggregated data with an application to downscaling

Sebastian Engelke, Raphaël Gérard Théodore Michel Marie de Deloÿe et Fourcade de Fondeville

The distribution of spatially aggregated data from a stochastic process may exhibit tail behaviour different from that of its marginal distributions. For a large class of aggregating functionals we introduce the -extremal coefficient, which quantifies this ...

OXFORD UNIV PRESS2019

Active contraction of cardiac cells: a reduced model for sarcomere dynamics with cooperative interactions

Alfio Quarteroni, Francesco Regazzoni

We propose a reduced ODE model for the mechanical activation of cardiac myofilaments, which is based on explicit spatial representation of nearest-neighbour interactions. Our model is derived from the cooperative Markov Chain model of Washio et al. (Cell M ...

SPRINGER HEIDELBERG2018

Semiparametric Bayesian Risk Estimation for Complex Extremes

Thomas Lugrin

Extreme events are responsible for huge material damage and are costly in terms of their human and economic impacts. They strike all facets of modern society, such as physical infrastructure and insurance companies through environmental hazards, banking an ...

EPFL2018

A Wasserstein-based measure of conditional dependence

Graph Chatbot

Chat with Graph Search

Geometrically-Conditioned Point Diffusion Models

The Gray-Wyner Network and Wyner's Common Information for Gaussian Sources

Quantifying uncertain system outputs via the multi-level Monte Carlo method --- distribution and robustness measures

Learning Constrained Distributions of Robot Configurations with Generative Adversarial Network

Distributionally Robust Optimization with Polynomial Densities: Theory, Models and Algorithms

On quantifying the quality of acoustic models in hybrid DNN-HMM ASR

Robust Generalization via $\alpha$-Mutual Information

Extremal behaviour of aggregated data with an application to downscaling

Active contraction of cardiac cells: a reduced model for sarcomere dynamics with cooperative interactions

Semiparametric Bayesian Risk Estimation for Complex Extremes

Geometrically-Conditioned Point Diffusion Models

The Gray-Wyner Network and Wyner's Common Information for Gaussian Sources

Extremal behaviour of aggregated data with an application to downscaling

Active contraction of cardiac cells: a reduced model for sarcomere dynamics with cooperative interactions

Robust Generalization via $\alpha$-Mutual Information

Distributionally Robust Optimization with Polynomial Densities: Theory, Models and Algorithms

Semiparametric Bayesian Risk Estimation for Complex Extremes

Quantifying uncertain system outputs via the multi-level Monte Carlo method --- distribution and robustness measures

Learning Constrained Distributions of Robot Configurations with Generative Adversarial Network

On quantifying the quality of acoustic models in hybrid DNN-HMM ASR