On the sub-Gaussianity of the Beta and Dirichlet distributions

Abstract

We obtain the optimal proxy variance for the sub-Gaussianity of Beta distribution, thus proving upper bounds recently conjectured by Elder (2016). We provide different proof techniques for the symmetrical (around its mean) case and the non-symmetrical case. The technique in the latter case relies on studying the ordinary differential equation satisfied by the Beta moment-generating function known as the confluent hypergeometric function. As a consequence, we derive the optimal proxy variance for the Dirichlet distribution, which is apparently a novel result. We also provide a new proof of the optimal proxy variance for the Bernoulli distribution, and discuss in this context the proxy variance relation to log-Sobolev inequalities and transport inequalities.

13 pages, 2 figures

References in corpus (3)

• Large Deviation Methods for Approximate Probabilistic Inference
• Bayesian Adaptive Data Analysis Guarantees from Subgaussianity
• Subgaussian sequences in probability and Fourier analysis

Cited by in corpus (7)

• Hierarchies, entropy, and quantitative propagation of chaos for mean field diffusions
• Saturation and recurrence of quantum complexity in random local quantum dynamics
• A multivariate normal approximation for the Dirichlet density and some applications
• Bernstein-Type Bounds for Beta Distribution
• A combinatorial view of stochastic processes: White noise
• Various New Inequalities for Beta Distributions
• A stochastic subspace approach to gradient-free optimization in high dimensions