Attend the Women in ML Symposium on December 7 Register now


Compute log(1 - exp(-|x|)) elementwise in a numerically stable way.

x Float Tensor.
name Python str name prefixed to Ops created by this function. Default value: None (i.e., 'log1mexp').

log1mexp Float Tensor of log1mexp(x).


[1]: Machler, Martin. Accurately computing log(1 - exp(-|a|))