Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Display (8) — distance to Algorithm 1’s target

Proved
ApproachRegret.ToOLO.display8_distance

by mikedeng1 · Oct 4, 2026 · Mathlib 0df444a (Lean v4.33.1)

blackwell-approachabilityconic-dualityp2o-batch-pfp1ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let K⊆RdK\subseteq\mathbb R^dK⊆Rd be nonempty, compact, and convex, with κ=max⁡x∈K∥x∥>0\kappa=\max_{x\in K}\|x\|>0κ=maxx∈K​∥x∥>0. Let S=cone⁡({κ}×K)0S=\operatorname{cone}(\{\kappa\}\times K)^0S=cone({κ}×K)0. For every z∈Rd+1z\in\mathbb R^{d+1}z∈Rd+1,

dist⁡(z,S)=max⁡w∈cone⁡({κ}×K)∩B2(1)⟨z,w⟩.\operatorname{dist}(z,S)=\max_{w\in\operatorname{cone}(\{\kappa\}\times K)\cap B_2(1)}\langle z,w\rangle.dist(z,S)=w∈cone({κ}×K)∩B2​(1)max​⟨z,w⟩.

The maximum is attained. Substituting the average payoff of Algorithm 1 yields the paper's displayed identity for its approachability rate.

Formalization Note The display's cone⁡(κ⊕K)\operatorname{cone}(\kappa\oplus K)cone(κ⊕K) means the cone of the lifted set {κ}×K\{\kappa\}\times K{κ}×K; its ball is in Rd+1\mathbb R^{d+1}Rd+1, although the display labels it with dimension ddd.

Preamble
import Mathlib
import Definitions.Def_ApproachRegret_ToOLO_AlgorithmOne

open scoped RealInnerProductSpace
Formal statement
namespace ApproachRegret.ToOLO

/-- Display (8), p. 37, for an arbitrary point in the lifted Euclidean space. -/
theorem display8_distance {d : ℕ} (K : Set (E d)) (z : E (d + 1))
    (hK : IsCompact K) (hconv : Convex ℝ K) (hne : K.Nonempty)
    (hk : 0 < kappa K) :
    IsGreatest ((fun w : E (d + 1) => ⟪z, w⟫) ''
      (cone (lift (kappa K) '' K) ∩ Metric.closedBall 0 1))
      (Metric.infDist z (target K)) := by sorry

end ApproachRegret.ToOLO
Source
Abernethy, Bartlett, Hazan, Blackwell Approachability and No-Regret Learning are Equivalent, COLT 2011, JMLR W&CP 19, https://proceedings.mlr.press/v19/abernethy11b.html, proof of Theorem 16, display (8), p. 37 (PDF p. 11)
Human review
  • Endorsed by Shuze Chen · Oct 4, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 4, 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