Probability distribution API of Beta and KL-Divergence

[cxxly]

PR types

New features

PR changes

APIs

Describe

• add Beta probability distribution, including mean, variance, sample, entropy, prob, log_prob method
• add kl_divergence and register_kl API，and register implementation functions <Beta, Beta> <Dirichlet, Dirichlet> <ExponentialFamily, Exponentialfamily> <Normal, Normal> <Categorical, Categorical> <Uniform, Uniform>
• fix some problems in add ExponentialFamily and Dirichlet probability distribution #38445

Examples

import paddle

# beta distribution
beta = paddle.distribution.Beta(alpha=0.5, beta=0.5)
print(beta.mean)

# kl divergence
p = paddle.distribution.Beta(alpha=0.5, beta=0.5)
q = paddle.distribution.Beta(alpha=0.3, beta=0.7)
print(paddle.distribution.kl_divergence(p, q))

# register kl
@paddle.distribution.register_kl(paddle.distribution.Beta, paddle.distribution.Beta)
def kl_beta_beta():
    pass # insert implementation here

[paddle-bot-old]

Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

[iclementine]

LGTM

[jeff41404]

LGTM

[XiaoguangHu01]

LG API