jensen_shannon_regularized_generator
def
The regularized generator with parameter c is f_c(x) = f_{JS}(x) + c x log x.
Statement
noncomputable def jensen_shannon_regularized_generator (c x : ℝ) : ℝ
- Defined in
- arXiv:2610.21231, Section II, Example 1(3)
- Verified
- 03 Nov 2026
- Axioms
- none listed
- Built on 1
- jensen_shannon_generatorThe f-divergence generator for Jensen-Shannon divergence is f(x) = (1/2) x log x - ((x + 1)/2) log((x + 1)/2).
- Used by 1
- jensen_shannon_regularized_generator_oneFor any parameter c, the regularized generator evaluates to 0 at 1: f_c(1) = 0.
Read back from the Lean
The function jensen_shannon_regularized_generator takes two real numbers $c$ and $x$ and returns the real number jensen_shannon_generator x + c * (x * Real.log x).
Written by a model that saw only the Lean, never the English above. If the two disagree, that is worth a challenge.
Lean source view module on GitHub
/-- The regularized generator obtained by adding c times the Shannon information generator x log x to the Jensen-Shannon generator. -/ noncomputable def jensen_shannon_regularized_generator (c x : ℝ) : ℝ := jensen_shannon_generator x + c * (x * Real.log x)