Sub-Gaussian property for the Beta distribution (part 3, final)

Posted in General, R by Julyan Arbel on 26 December 2017

When a Beta random variable wants to act like a Bernoulli: convergence of optimal proxy variance.

In this third and last post about the Sub-Gaussian property for the Beta distribution [1] (post 1 and post 2), I would like to show the interplay with the Bernoulli distribution as well as some connexions with optimal transport (OT is a hot topic in general, and also on this blog with Pierre’s posts on Wasserstein ABC).

Let us see how sub-Gaussian proxy variances can be derived from transport inequalities. To this end, we need first to introduce the Wasserstein distance (of order 1) between two probability measures P and  Q on a space \mathcal{X}. It is defined wrt a distance d on \mathcal{X} by


where \Pi(P,Q) is the set of probability measures on \mathcal{X}\times \mathcal{X} with fixed marginal distributions respectively P and Q. Then, a probability measure P is said to satisfy a transport inequality with positive constant \sigma, if for any probability measure Q dominated by P,

W(P,Q) \leq\sigma\sqrt{2 D(Q||P)},

where D(Q||P) is the entropy, or Kullback–Leibler divergence, between P and Q. The nice result proven by Bobkov and Götze (1999) [2] is that the constant \sigma^2 is a sub-Gaussian proxy variance for P.

For a discrete space \mathcal{X} equipped with the Hamming metric, d(x,y) = \mathbf{1}_{\{x\neq y\}}, the induced Wasserstein distance reduces to the total variation distance, W(P,Q) = \Vert P-Q\Vert_{\text{TV}}. In that setting, Ordentlich and Weinberger (2005) [3] proved the distribution-sensitive transport inequality:

\Vert P-Q\Vert_{\text{TV}} \leq \sqrt{\frac{1}{g(\mu_P)}D(Q||P)},

where the function g is defined by g(\mu)=\frac{1}{1-2\mu}\ln\frac{1-\mu}{\mu} and the coefficient \mu_P is called the balance coefficient of P, and is defined by \mu_P=\underset{A\subset \mathcal{X}}\max\min\{P(A),1-P(A)\}. In particular, the Bernoulli balance coefficient is easily shown to coincide with its mean. Hence, applying the result of Bobkov and Götze (1999) [2] to the above transport inequality yields a distribution-sensitive proxy variance of \frac{1}{2g(\mu)}=\frac{1-2\mu}{2\ln((1-\mu)/\mu)} for the Bernoulli with mean \mu, as plotted in blue above.

In the Beta distribution case, we have not been able to extend this transport inequality methodology since the support is not discrete. However, a nice limiting argument holds. Consider a sequence of Beta(\alpha,\beta) random variables with fixed mean \mu=\frac{\alpha}{\alpha+\beta} and with a sum \alpha+\beta going to zero. This converges to a Bernoulli random variable with mean \mu, and we have shown that the limiting optimal proxy variance of such a sequence of Beta with decreasing sum \alpha+\beta is the one of the Bernoulli.


[1] Marchal, O. and Arbel, J. (2017), On the sub-Gaussianity of the Beta and Dirichlet distributions. Electronic Communications in Probability, 22:1–14, 2017. Code on GitHub.
[2] Bobkov, S. G. and Götze, F. (1999). Exponential integrability and transportation cost related to logarithmic Sobolev inequalities. Journal of Functional Analysis, 163(1):1–28.
[3] Ordentlich, E. and Weinberger, M. J. (2005). A distribution dependent refinement of Pinsker’s inequality. IEEE Transactions on Information Theory, 51(5):1836–1840.


4 Responses

Subscribe to comments with RSS.

  1. Alex said, on 20 January 2018 at 16:17

    I’m now not positive the place you’re getting your info, but good topic. I needs to spend a while studying more or figuring out more. Thank you for wonderful info I was on the lookout for this info for my mission.

  2. Alex said, on 20 January 2018 at 19:44

    Excellent blog here! Additionally your web site quite a bit up very fast! What web host are you the usage of? Can I get your associate link for your host? I desire my web site loaded up as fast as yours lol

  3. Alex said, on 20 January 2018 at 21:27

    I am no longer sure the place you are getting your info, however good topic. I must spend some time finding out much more or working out more. Thank you for excellent info I used to be looking for this info for my mission.

  4. Alex said, on 21 January 2018 at 10:31

    You actually make it appear so easy with your presentation but I in finding this matter to be actually one thing which I think I’d by no means understand. It kind of feels too complex and very large for me. I’m taking a look forward to your next put up, I’ll try to get the grasp of it!

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: