News for hackers. Stuff that matters.
Re:Continuous Bernoulli distribution of Variational autoenco... by canjobear on Saturday November 28, 2020 @03:09AM (#25236121)
What is the Continuous Bernoulli distribution good for?

Edit: I see it’s equivalent to a Beta distribution.

Re:Continuous Bernoulli distribution of Variational autoenco... by alentist on Saturday November 28, 2020 @04:34PM (#25240757)
> I see it’s equivalent to a Beta distribution.

It's not.

The beta distribution is p(x) ∝ x^(α-1) (1-x)^(β-1). x is in the bases.

The continuous Bernoulli distribution is p(x) ∝ λ^x (1-λ)^x. x is in the exponents.

As https://arxiv.org/abs/1907.06845 says:

> the continuous Bernoulli is not a beta distribution (the main difference between these two distributions is how they concentrate mass around the extrema, see appendix 1 for details)

The appendix is available here (under "Supplemental"): https://papers.nips.cc/paper/2019/hash/f82798ec8909d23e55679...

Re:Continuous Bernoulli distribution of Variational autoenco... by blackbear_ on Saturday November 28, 2020 @04:58AM (#25236629)
Not even a full-blown beta distribution, just a special case. And it was published in neurips...
Re:Continuous Bernoulli distribution of Variational autoenco... by alentist on Saturday November 28, 2020 @04:39PM (#25240791)
This is not correct. See above.