In probability theory, statistics, and machine learning, the continuous Bernoulli distribution[1][2][3] is a family of continuous probability distributions parameterized by a single shape parameter , defined on the unit interval , by:
The continuous Bernoulli distribution arises in deep learning and computer vision, specifically in the context of variational autoencoders,[4][5] 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, -valued data.[6][7][8][9] 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, -valued data.
The continuous Bernoulli also defines an exponential family of distributions. Writing for the natural parameter, the density can be rewritten in canonical form:
.
^Loaiza-Ganem, G., & Cunningham, J. P. (2019). The continuous Bernoulli: fixing a pervasive error in variational autoencoders. In Advances in Neural Information Processing Systems (pp. 13266-13276).
^Tensorflow Probability. https://www.tensorflow.org/probability/api_docs/python/tfp/edward2/ContinuousBernoulli Archived 2020-11-25 at the Wayback Machine
^Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114.
^Kingma, D. P., & Welling, M. (2014, April). Stochastic gradient VB and the variational auto-encoder. In Second International Conference on Learning Representations, ICLR (Vol. 19).
^Larsen, A. B. L., Sønderby, S. K., Larochelle, H., & Winther, O. (2016, June). Autoencoding beyond pixels using a learned similarity metric. In International conference on machine learning (pp. 1558-1566).
^Jiang, Z., Zheng, Y., Tan, H., Tang, B., & Zhou, H. (2017, August). Variational deep embedding: an unsupervised and generative approach to clustering. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (pp. 1965-1972).
statistics, and machine learning, the continuousBernoullidistribution is a family of continuous probability distributions parameterized by a single shape...
statistics, the continuous uniform distributions or rectangular distributions are a family of symmetric probability distributions. Such a distribution describes...
and statistics, the Bernoullidistribution, named after Swiss mathematician Jacob Bernoulli, is the discrete probability distribution of a random variable...
probability distribution for the Bernoulli, binomial, negative binomial, and geometric distributions. The formulation of the beta distribution discussed...
distribution, for absolutely continuously distributed values Basic distributions: Bernoullidistribution, for the outcome of a single Bernoulli trial (e.g. success/failure...
Many probability distributions that are important in theory or applications have been given specific names. The Bernoullidistribution, which takes value...
single trial, i.e., n = 1, the binomial distribution is a Bernoullidistribution. The binomial distribution is the basis for the popular binomial test...
Bernoulli family of Basel. Bernoulli differential equation BernoullidistributionBernoulli number Bernoulli polynomials Bernoulli process Bernoulli Society...
distribution may be viewed as a continuous counterpart of the geometric distribution, which describes the number of Bernoulli trials necessary for a discrete...
In the theory of probability and statistics, a Bernoulli trial (or binomial trial) is a random experiment with exactly two possible outcomes, "success"...
associated with a Bernoulli trial or experiment. They all have the same Bernoullidistribution. Much of what can be said about the Bernoulli process can also...
probability theory and statistics, the Laplace distribution is a continuous probability distribution named after Pierre-Simon Laplace. It is also sometimes...
second coin flips respectively. Each coin flip is a Bernoulli trial and has a Bernoullidistribution. If a coin displays "heads" then the associated random...
1, the multinomial distribution is the Bernoullidistribution. When k is 2 and n is bigger than 1, it is the binomial distribution. When k is bigger than...
x_{m}\ } is unknown). Another example: Bernoulli-type distributions – binomial, negative binomial, geometric distribution, and similar – can only be included...
theory and statistics, a normal distribution or Gaussian distribution is a type of continuous probability distribution for a real-valued random variable...
theory and statistics, the logistic distribution is a continuous probability distribution. Its cumulative distribution function is the logistic function...
{Dir} ({\boldsymbol {\alpha }})} , is a family of continuous multivariate probability distributions parameterized by a vector α {\displaystyle {\boldsymbol...
In mathematics, the Bernoulli numbers Bn are a sequence of rational numbers which occur frequently in analysis. The Bernoulli numbers appear in (and can...
since although its cumulative distribution function is a continuous function, the distribution is not absolutely continuous with respect to Lebesgue measure...
variables are continuous, for example in continuous optimization problems. In statistical theory, the probability distributions of continuous variables can...
and are unique to a given distribution.[citation needed] The convolution of two independent identically distributed Bernoulli random variables is a binomial...
being independent of the past states). A Bernoulli scheme with only two possible states is known as a Bernoulli process. Note, however, by the Ornstein...
statistics, the skew normal distribution is a continuous probability distribution that generalises the normal distribution to allow for non-zero skewness...
Jacob Bernoulli (also known as James in English or Jacques in French; 6 January 1655 [O.S. 27 December 1654] – 16 August 1705) was one of the many prominent...
geometric distribution is either one of two discrete probability distributions: The probability distribution of the number X {\displaystyle X} of Bernoulli trials...