Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition C.2(i), p. 34 — D_h(p, x) < +∞ whenever x ∈ Δ_p

Proved
ReinfRegGames.StrictStable.proposition_C_2_i

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

bregman-divergenceconvex-analysisp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1penalty-function

Let hhh be a KKK-strongly convex penalty function on Δ=Δ(B)\Delta=\Delta(B)Δ=Δ(B) and p∈Δp\in\Deltap∈Δ. h′(x;p−x)=lim⁡t→0+t−1[h(x+t(p−x))−h(x)]h'(x;p-x)=\lim_{t\to0^+}t^{-1}[h(x+t(p-x))-h(x)]h′(x;p−x)=limt→0+​t−1[h(x+t(p−x))−h(x)] is the one-sided derivative (C.3) and Dh(p,x)=h(p)−h(x)−h′(x;p−x)D_h(p,x)=h(p)-h(x)-h'(x;p-x)Dh​(p,x)=h(p)−h(x)−h′(x;p−x) is the Bregman divergence (C.4), which may equal +∞+\infty+∞ when h′(x;p−x)=−∞h'(x;p-x)=-\inftyh′(x;p−x)=−∞. Δp={x∈Δ:xα>0 whenever pα>0}\Delta_p=\{x\in\Delta: x_\alpha>0\text{ whenever }p_\alpha>0\}Δp​={x∈Δ:xα​>0 whenever pα​>0} is the union of the relative interiors of the faces of Δ\DeltaΔ that contain ppp (C.5).

If x∈Δpx\in\Delta_px∈Δp​, then the one-sided derivative h′(x;p−x)h'(x;p-x)h′(x;p−x) exists as a real number; in particular

Dh(p,x)<+∞for all x∈Δp.D_h(p,x)<+\infty\qquad\text{for all }x\in\Delta_p .Dh​(p,x)<+∞for all x∈Δp​.

Near a vertex x∗x^*x∗, every point of Δ\DeltaΔ lies in Δx∗\Delta_{x^*}Δx∗​, so the Bregman divergence Dh(x∗,⋅)D_h(x^*,\cdot)Dh​(x∗,⋅) is finite there; the proof of Theorem 5.2 uses this to build the neighbourhood UεU_\varepsilonUε​ of x∗x^*x∗.

Formalization Note The one-sided derivative is encoded as the predicate "the difference quotient t−1[h(x+t(p−x))−h(x)]t^{-1}[h(x+t(p-x))-h(x)]t−1[h(x+t(p−x))−h(x)] tends to ddd as t→0+t\to0^+t→0+" with ddd real, and Dh(p,x)D_h(p,x)Dh​(p,x) as h(p)−h(x)−dh(p)-h(x)-dh(p)−h(x)−d; no real-valued function with a junk value stands for +∞+\infty+∞.

Preamble
import Mathlib
import Definitions.Def_agt_games
import Definitions.Def_ReinfRegGames_Extinction_Model
Formal statement
namespace ReinfRegGames.StrictStable

theorem proposition_C_2_i {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)
    (hxp : ∀ α, 0 < p α → 0 < x α) :
    ∃ d : ℝ, Filter.Tendsto (fun t : ℝ => (h (x + t • (p - x)) - h x) / t) (nhdsWithin 0 (Set.Ioi 0)) (nhds d) := by sorry

end ReinfRegGames.StrictStable
Source
Mertikopoulos & Sandholm, Learning in games via reinforcement and regularization, arXiv:1407.6267v2, pp. 33–34, Proposition C.2(i), with (C.3)–(C.5)
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me