Mutual information

By Andreu Arinyo-i-Prats, Víctor J. López-Madrona, M. Paluš, J. López-Madrona. Encyclopedia of Biometrics, 2009

387 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Information Systems, Transportation

View Paper: https://www.semanticscholar.org/paper/c51807126b600a40705b0e48e75e993190b927b4

How researchers see this paper

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

In Aerospace Engineering

1. Bo Li
2. Philip S. Yu
3. Flávio du Pin Calmon
4. Sergio Verdú
5. Paul W. Cuff
6. Shuo-Hui Li
7. Lanqing Yu
8. Lei Wang

In Information Systems

1. Bo Li
2. Philip S. Yu
3. Flávio du Pin Calmon
4. Paul W. Cuff
5. Renato Renner
6. Shuo-Hui Li
7. Hao Wang
8. Peter Kairouz

In Transportation

1. Philip S. Yu
2. Paul W. Cuff
3. Shuo-Hui Li
4. Peter Kairouz
5. Lanqing Yu
6. Lichao Sun
7. Lei Wang

Citations in the corpus

• Discovering physical concepts with neural networks (2018, background): “Another step towards extracting physical knowledge in an unsupervised way is presented in [18].”
• Adversarial Attack and Defense on Graph Data: A Survey (2018, methodology): “Normalized Mutual Information ( NMI ) [134] and Modularity [133] are two metrics used by [22], [23], [150] to evaluate the performance of community detection (i.e., clustering) on graphs.”
• Differential Privacy as a Mutual Information Constraint (2016, methodology): “If the mechanism P Y | X n satisfies ǫ -DP, then sup Furthermore, for α > 0, when maximizing over database distributions P X n , all three notions of α -mutual-information discussed in [24] are equivalent.”
• Convexity/concavity of renyi entropy and α-mutual information (2015, background): “This notion of mutual information was introduced by Sibson [10] in the discrete case, as the information radius of order α [11].”
• Context-Aware Generative Adversarial Privacy (2017, background): “Information-theoretic metrics, and in particular MI privacy, allow the use of Fano’s inequality and its variants [79] to bound the rate of learning the private variables for a variety of learning metrics, such as error probability and minimum mean-squared error (MMSE).”
• On the Robustness of Information-Theoretic Privacy Measures and Mechanisms (2018, background): “Recall that lim α→∞ I S α(PX,Y ) = I S ∞(PX,Y ) [31].”
• A statistical framework for neuroimaging data analysis based on mutual information estimated via a gaussian copula (2016, background): “Entropy is the foundational quantity of information theory and is a measure of the uncertainty, or variability, of a random variable.”
• Neural Network Renormalization Group (2018, methodology): “[24] proposed an RG scheme based on mutual information maximization, Ref.”