Differentiable approximations to the min and max operators
1–3 of 3 posts
Re: Differentiable approximations to the min and max operators
#2tl;dr
1. Within the context of optimisation, differentiable approximations of the min and max operators on R^n are very useful.
2. However, in order for these approximations to be useful they must also be numerically stable.
Re: Differentiable approximations to the min and max operators
#3How does this stack up to the softmax[0] function, log(exp(n_1) + exp(n_2) + ... + exp(n_i))? Are they analytically equivalent?