Proposition C.2(ii), p. 34 — D_h(p, x) ≥ 0, D_h(p, x) = 0 iff p = x, and D_h(p, x) ≥ ½K ‖x − p‖² (C.6)
ProvedReinfRegGames.StrictStable.proposition_C_2_iiLet be a -strongly convex penalty function on and . is the one-sided derivative (C.3) and is the Bregman divergence (C.4), which may equal when . is the union of the relative interiors of the faces of that contain (C.5).
For every , , if and only if , and
The Bregman divergence is thus a (non-symmetric) measure of proximity to , bounded below by the squared distance.
Formalization Note The one-sided derivative is encoded as the predicate "the difference quotient tends to as " with real, and as ; no real-valued function with a junk value stands for . The statement is made for every at which the one-sided derivative is a real number ; where the page's and all three claims hold trivially, so this is the faithful form. The norm in the strong convexity inequality (2.5) is the Euclidean one; the page leaves it unspecified, and since is existential in Definition 2.1 the class of penalty functions does not depend on this choice, but the constant does.
import Mathlib import Definitions.Def_agt_games import Definitions.Def_ReinfRegGames_Extinction_Model
namespace ReinfRegGames.StrictStable
theorem proposition_C_2_ii {B : Type*} [Fintype B] (h : (B → ℝ) → ℝ) (K : ℝ) (hpen : ReinfRegGames.Extinction.IsPenalty h K)
(p : B → ℝ) (hp : p ∈ stdSimplex ℝ B) (x : B → ℝ) (hx : x ∈ stdSimplex ℝ B) (d : ℝ)
(hd : Filter.Tendsto (fun t : ℝ => (h (x + t • (p - x)) - h x) / t) (nhdsWithin 0 (Set.Ioi 0)) (nhds d)) :
0 ≤ h p - h x - d ∧ (h p - h x - d = 0 ↔ p = x) ∧
1 / 2 * K * ReinfRegGames.Extinction.sqDist x p ≤ h p - h x - d := by sorry
end ReinfRegGames.StrictStable
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.