Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition C.2(iii), p. 34 — Dh(p,xj)→Dh(p,x)D_h(p,x_j)\to D_h(p,x)Dh​(p,xj​)→Dh​(p,x) whenever xj→xx_j\to xxj​→x in Δp\Delta_pΔp​

Proved
ReinfRegGames.Extinction.proposition_C_2_iii

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

bregman-divergencecontinuityconvex-analysisp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let hhh be a KKK-strongly convex penalty function on the simplex Δ\DeltaΔ and p∈Δp\in\Deltap∈Δ. Let (xj)j≥0(x_j)_{j\ge0}(xj​)j≥0​ be a sequence in Δp\Delta_pΔp​ converging to a point x∈Δpx\in\Delta_px∈Δp​. Let dj=h′(xj;p−xj)d_j=h'(x_j;p-x_j)dj​=h′(xj​;p−xj​) and d=h′(x;p−x)d=h'(x;p-x)d=h′(x;p−x) be the (real) one-sided derivatives of (C.3). Then the Bregman divergences converge:

Dh(p,xj)=h(p)−h(xj)−dj ⟶ h(p)−h(x)−d=Dh(p,x)(j→∞).D_h(p,x_j)=h(p)-h(x_j)-d_j\ \longrightarrow\ h(p)-h(x)-d=D_h(p,x)\qquad (j\to\infty).Dh​(p,xj​)=h(p)−h(xj​)−dj​ ⟶ h(p)−h(x)−d=Dh​(p,x)(j→∞).

Continuity of Dh(p,⋅)D_h(p,\cdot)Dh​(p,⋅) on Δp\Delta_pΔp​ is the second ingredient, with (C.11), of Proposition C.4.

Formalization Note By Proposition C.2(i) the one-sided derivatives at points of Δp\Delta_pΔp​ are real numbers; the statement takes them as data satisfying the predicate HasOneSidedDeriv.

Preamble
import Mathlib
import Definitions.Def_agt_games
import Definitions.Def_ReinfRegGames_Extinction_Model
import Definitions.Def_ReinfRegGames_Extinction_Bregman
Formal statement
namespace ReinfRegGames.Extinction

open Filter Topology

theorem proposition_C_2_iii {B : Type*} [Fintype B] (h : (B → ℝ) → ℝ) (K : ℝ) (hpen : IsPenalty h K)
    (p : B → ℝ) (hp : p ∈ stdSimplex ℝ B) (xs : ℕ → B → ℝ) (x : B → ℝ)
    (hxs : ∀ j, xs j ∈ deltaP p) (hx : x ∈ deltaP p) (hlim : Tendsto xs atTop (𝓝 x))
    (ds : ℕ → ℝ) (d : ℝ) (hds : ∀ j, HasOneSidedDeriv h (xs j) (p - xs j) (ds j))
    (hd : HasOneSidedDeriv h x (p - x) d) :
    Tendsto (fun j => h p - h (xs j) - ds j) atTop (𝓝 (h p - h x - d)) := by sorry

end ReinfRegGames.Extinction
Source
Mertikopoulos & Sandholm, Learning in games via reinforcement and regularization, arXiv:1407.6267v2, p. 34, Proposition C.2(iii)
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