Continuous Bernoulli distribution

Not to be confused with Bernoulli distribution.

Continuous Bernoulli distribution
Probability density function
Parameters	$\lambda =1/(1+e^{-\theta })\in (0,1)$	$\theta \in \mathbb {R}$, natural parameter
Support	$x\in [0,1]$	$x\in [0,1]$
PDF	$C(\lambda )\lambda ^{x}(1-\lambda )^{1-x}\!$ where $C(\lambda )={\begin{cases}2&{\text{if }}\lambda ={\frac {1}{2}}\\{\frac {2\tanh ^{-1}(1-2\lambda )}{1-2\lambda }}&{\text{ otherwise}}\end{cases}}$	$f(x\mid \theta )={\begin{cases}1&\theta =0\\\exp(x\theta -\log\{(e^{\theta }-1)/\theta \})&\theta \neq 0\end{cases}}$
CDF	$F(x\mid \lambda )={\begin{cases}x,&\lambda ={\tfrac {1}{2}}\\[6pt]{\dfrac {\lambda ^{x}(1-\lambda )^{1-x}+\lambda -1}{2\lambda -1}},&{\text{otherwise}}\end{cases}}$	$F(x\mid \theta )={\begin{cases}x&\theta =0\\(e^{\theta x}-1)/(e^{\theta }-1)&\theta \neq 0\end{cases}}$
Mean	$\operatorname {E} [X]={\begin{cases}{\tfrac {1}{2}}&\lambda ={\tfrac {1}{2}}\\[6pt]{\dfrac {\lambda }{2\lambda -1}}+{\dfrac {1}{2\tanh ^{-1}(1-2\lambda )}},&{\text{otherwise}}\end{cases}}$	$\operatorname {E} [X]={\begin{cases}1/2&\theta =0\\e^{\theta }/(e^{\theta }-1)-\theta ^{-1}&\theta \neq 0\end{cases}}$
Variance	$\operatorname {Var} (X)={\begin{cases}{\tfrac {1}{12}},&\lambda ={\tfrac {1}{2}}\\[6pt]-{\dfrac {\lambda (1-\lambda )}{(1-2\lambda )^{2}}}+{\dfrac {1}{(2\tanh ^{-1}(1-2\lambda ))^{2}}},&{\text{otherwise}}\end{cases}}$	$\operatorname {Var} (X)={\begin{cases}1/12&\theta =0\\(2-e^{\theta }-e^{-\theta })^{-1}+\theta ^{2}&\theta \neq 0\end{cases}}$

In probability theory, statistics, and machine learning, the continuous Bernoulli distribution is a family of continuous probability distributions parameterized by a single shape parameter $\lambda \in (0,1)$, defined on the unit interval $x\in [0,1]$, by:

$p(x|\lambda )\propto \lambda ^{x}(1-\lambda )^{1-x}.$

The continuous Bernoulli distribution arises in deep learning and computer vision, specifically in the context of variational autoencoders, for modeling the pixel intensities of natural images. As such, it defines a proper probabilistic counterpart for the commonly used binary cross entropy loss, which is often applied to continuous, $[0,1]$-valued data. This practice amounts to ignoring the normalizing constant of the continuous Bernoulli distribution, since the binary cross entropy loss only defines a true log-likelihood for discrete, $\{0,1\}$-valued data.

The continuous Bernoulli also defines an exponential family of distributions. Writing $\theta =\log \left(\lambda /(1-\lambda )\right)$ for the natural parameter, the density can be rewritten in canonical form: $p(x|\theta )\propto \exp(\theta x)$.

Statistical inference

Given an independent sample of $n$ points $x_{1},\dots ,x_{n}$ with $x_{i}\in [0,1]\,\forall i$ from continuous Bernoulli, the log-likelihood of the natural parameter $\theta$ is

${\mathcal {L}}(\theta )=\theta \sum _{i=1}^{n}x_{i}-n\log\{(e^{\theta }-1)/\theta \}$

and the maximum likelihood estimator of the natural parameter $\theta$ is the solution of ${\mathcal {L}}'(\theta )=0$, that is, ${\hat {\theta }}$ satisfies

${\frac {e^{\hat {\theta }}}{e^{\hat {\theta }}-1}}-{\frac {1}{\hat {\theta }}}={\frac {1}{n}}\sum _{i=1}^{n}x_{i}$

where the left hand side $e^{\hat {\theta }}/(e^{\hat {\theta }}-1)-{\hat {\theta }}^{-1}$ is the expected value of continuous Bernoulli with parameter ${\hat {\theta }}$. Although ${\hat {\theta }}$ does not admit a closed-form expression, it can be easily calculated with numerical inversion.

Further properties

The entropy of a continuous Bernoulli distribution is

$\operatorname {H} [X]={\begin{cases}0&{\text{ if }}\lambda ={\frac {1}{2}}\\{\frac {\lambda \log \left(\lambda \right)-\left(1-\lambda \right)\log \left(1-\lambda \right)}{1-2\lambda }}-\log \left({\frac {2\tanh ^{-1}\left(1-2\lambda \right)}{e\left(1-2\lambda \right)}}\right)&{\text{ otherwise}}\end{cases}}\!$

Related distributions

Bernoulli distribution

The continuous Bernoulli can be thought of as a continuous relaxation of the Bernoulli distribution, which is defined on the discrete set $\{0,1\}$ by the probability mass function:

$p(x)=p^{x}(1-p)^{1-x},$

where $p$ is a scalar parameter between 0 and 1. Applying this same functional form on the continuous interval $[0,1]$ results in the continuous Bernoulli probability density function, up to a normalizing constant.

Uniform distribution

The Uniform distribution between the unit interval [0,1] is a special case of continuous Bernoulli when $\lambda =1/2$ or $\theta =0$.

Exponential distribution

An exponential distribution with rate $\Lambda$ restricted to the unit interval [0,1] corresponds to a continuous Bernoulli distribution with natural parameter $\theta =-\Lambda <0$.

Continuous categorical distribution

The multivariate generalization of the continuous Bernoulli is called the continuous-categorical.