Concept

Gibbs' inequality

Related publications (19)

Edge colorings of graphs without monochromatic stars

In this note, we improve on results of Hoppen, Kohayakawa and Lefmann about the maximum number of edge colorings without monochromatic copies of a star of a fixed size that a graph on n vertices may admit. Our results rely on an improved application of an ...

ELSEVIER2020

On Vacuous and Non-Vacuous Generalization Bounds for Deep Neural Networks.

Konstantinos Pitas

Deep neural networks have been empirically successful in a variety of tasks, however their theoretical understanding is still poor. In particular, modern deep neural networks have many more parameters than training data. Thus, in principle they should over ...

EPFL2020

Fast Mean Estimation with Sub-Gaussian Rates

Nicolas Henri Bernard Flammarion

We present an improved analysis of the Euler-Maruyama discretization of the Langevin diffusion. Our analysis does not require global contractivity, and yields polynomial dependence on the time horizon. Compared to existing approaches, we make an additional ...

2019

Mean-Field methods for Structured Deep-Learning in Computer Vision

Pierre Bruno Baqué

In recent years, Machine Learning based Computer Vision techniques made impressive progress. These algorithms proved particularly efficient for image classification or detection of isolated objects. From a probabilistic perspective, these methods can predi ...

EPFL2018

Multi-Modal Mean-Fields via Cardinality-Based Clamping

Pascal Fua, François Fleuret

Mean Field inference is central to statistical physics. It has attracted much interest in the Computer Vision community to efficiently solve problems expressible in terms of large Conditional Random Fields. However, since it models the posterior probabilit ...

Ieee2017

Multi-Modal Mean-Fields via Cardinality-Based Clamping

Pascal Fua, François Fleuret

Ieee2017

Distributed inference over regression and classification models

Ali H. Sayed

We study the distributed inference task over regression and classification models where the likelihood function is strongly log-concave. We show that diffusion strategies allow the KL divergence between two likelihood functions to converge to zero at the r ...

IEEE2013

Refined Support and Entropic Uncertainty Inequalities

Benjamin Ricaud

Generalized versions of the entropic (Hirschman-Beckner) and support (Elad-Bruckstein) uncertainty principle are presented for frames representations. Moreover, a sharpened version of the support inequality is obtained by introducing a generalization of th ...

Ieee-Inst Electrical Electronics Engineers Inc2013

Lower and upper bounds for approximation of the Kullback-Leibler divergence between Gaussian Mixture Models

Jean-Philippe Thiran, Finnian Paul Kelly

Many speech technology systems rely on Gaussian Mixture Models (GMMs). The need for a comparison between two GMMs arises in applications such as speaker verification, model selection or parameter estimation. For this purpose, the Kullback-Leibler (KL) dive ...

Ieee2012

An entropy inequality for q-ary random variables and its application to channel polarization

Eren Sasoglu

It is shown that given two copies of a q-ary input channel W, where q is prime, it is possible to create two channels W- and W+ whose symmetric capacities satisfy I(W-)

Ieee Service Center, 445 Hoes Lane, Po Box 1331, Piscataway, Nj 08855-1331 Usa2010

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.