Rényi divergence measures for commonly used univariate continuous distributions

By M. Ángeles Gil, Fady Alajaji, Tamás Linder. 2013

153 citations recorded by the source corpus.

Subfields: Statistical and Nonlinear Physics, Statistics and Probability

How researchers see this paper

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

In Statistical and Nonlinear Physics

1. Borja Balle
2. Yu-Xiang Wang
3. Shiva Prasad Kasiviswanathan
4. Sylvain Gelly
5. Mario Lucic
6. Olivier Bousquet
7. Marco Cuturi
8. Boi Faltings

In Statistics and Probability

1. Borja Balle
2. Yu-Xiang Wang
3. Shiva Prasad Kasiviswanathan
4. Olivier Bousquet
5. Marco Cuturi
6. Boi Faltings
7. Tim van Erven
8. Sylvain Gelly

Citations in the corpus

• Subsampled Rényi Differential Privacy and Analytical Moments Accountant (2018, background): “The Gaussian mechanism with variance σ 2 has a tight RDP parameter bound (cid:15) ( α ) = α 2 σ 2 (Gil et al., 2013).”
• Rényi Divergence and Kullback-Leibler Divergence (2012, methodology): “embers of the same exponential family, then their Renyi divergence can be computed using a´ formula by Huzurbazar [19] and Liese and Vajda [20, p.43], [11]. Gil provides a long list of examples [21], [22]. Example 1. Let Qbe a probability distribution and Aa set with positive probability. Let Pbe th”
• Federated Learning with Bayesian Differential Privacy (2019, background): “Analytic expressions for Rényi divergence exist for many common distributions and can be found in [30].”
• Precision-Recall Curves Using Information Divergence Frontiers (2019, methodology): “We analytically evaluate D α , where P is a Normal (Gil et al., 2013).”