| vi_log1p_abs {tfprobability} | R Documentation |
The log1p-abs Csiszar-function in log-space
Description
A Csiszar-function is a member of F = { f:R_+ to R : f convex }.
Usage
vi_log1p_abs(logu, name = NULL)
Arguments
logu |
|
name |
name prefixed to Ops created by this function. |
Details
The Log1p-Abs Csiszar-function is:
f(u) = u**(sign(u-1)) - 1
This function is so-named because it was invented from the following recipe. Choose a convex function g such that g(0)=0 and solve for f:
log(1 + f(u)) = g(log(u)). <=> f(u) = exp(g(log(u))) - 1
That is, the graph is identically g when y-axis is log1p-domain and x-axis
is log-domain.
Warning: this function makes non-log-space calculations and may
therefore be numerically unstable for |logu| >> 0.
Value
log1p_abs_of_u: float-like Tensor of the Csiszar-function
evaluated at u = exp(logu).
See Also
Other vi-functions:
vi_amari_alpha(),
vi_arithmetic_geometric(),
vi_chi_square(),
vi_csiszar_vimco(),
vi_dual_csiszar_function(),
vi_fit_surrogate_posterior(),
vi_jeffreys(),
vi_jensen_shannon(),
vi_kl_forward(),
vi_kl_reverse(),
vi_modified_gan(),
vi_monte_carlo_variational_loss(),
vi_pearson(),
vi_squared_hellinger(),
vi_symmetrized_csiszar_function()