Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)

By Thomas M. Cover, Joy A. Thomas. 2006

1,994 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Theory

Citations in the corpus

Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning (2020, neutral): “3 of [45]).”
Opening the Black Box of Deep Neural Networks via Information (2017, background): “The second is the Data Processing Inequality (DPI) [Cover and Thomas (2006)]: for any 3 variables that form a Markov chain X → Y → Z,”
Excessive Invariance Causes Adversarial Vulnerability (2018, background): “Consider the reformulation by the chain rule of mutual information (Cover & Thomas, 2006), where I ( y ; z n | z s ) denotes the conditional mutual information.”
Preventing Posterior Collapse with delta-VAEs (2019, methodology): “On ImageNet 32x32, our latent variable model achieves on par performance with purely autoregressive Image Transformer (Parmar et al., 2018).”
Distributed Uniformity Testing (2018, background): “m = Θ(|MA |/(f (τ )δ )) messages and condition the input on these messages, then with good probability we “neutralize” all but at most f (τ ) · δ of the difference, measured in KL-divergence [9] between”
Approximate Entropy and Sample Entropy: A Comprehensive Tutorial (2019, background): “Hence, the measurement of the entropy rate offers a way of measuring to what extent a process is stochastic and will ultimately quantify the randomness of a series [8] (p.”
Information based adaptive robotic exploration (2002, background): “Using Equations 15) and (18), it is possible to compute the expected mutual information gain following an observation ([1]):”
Quantum resource theories (2018, background): “Relative majorization has a very simple characterization in terms of testing regions (Renes, 2016), which can represent Neyman-Pearson hypothesis testing (Cover and Thomas, 2006).”
The Earth Mover's Distance as a Metric for Image Retrieval (2000, positive): “From the information theory point of view, the K-L divergence has the property that it measures how inefficient on average it would be to code one histogram using the other as the code-book ( Cover and Thomas, 1991 ).”
Modularity and community detection in bipartite networks. (2007, methodology): “In the present work, we will not make use of this algorithm, nor of a recursive bipartitioning approach, instead developing an alternative technique that capitalizes on the bipartite nature of the networks.”
“Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors (2018, background): “It is well known [12] that if X and Y are two independent random variables, the entropy of their sum Z = X + Y is larger than their individual entropies: max{H(X), H(Y )} ≤ H(Z).”
Continuous latent variable models for dimensionality reduction and sequential data reconstruction (2001, background): “For fixed variance, this index is minimised by the normal density (Cover and Thomas, 1991).”