Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 16 — approachability rate bounds OLO regret

Proved
ApproachRegret.ToOLO.theorem16_regret_le

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

blackwell-approachabilityonline-linear-optimizationp2o-batch-pfp1ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let K⊆RdK\subseteq\mathbb R^dK⊆Rd be nonempty, compact, and convex, and set κ=max⁡x∈K∥x∥>0\kappa=\max_{x\in K}\|x\|>0κ=maxx∈K​∥x∥>0. Feed each loss vector ft∈B2(1)f_t\in B_2(1)ft​∈B2​(1) to any algorithm AAA that selects a point of KKK from past admissible losses. Algorithm 1 uses that same decision as its OLO decision and evaluates it in the lifted Blackwell instance. For every horizon T≥1T\ge1T≥1,

Regret⁡T(A;f1:T)T≤2κ DT(A;f1:T),\frac{\operatorname{Regret}_T(A;f_{1:T})}{T}\le 2\kappa\,D_T(A;f_{1:T}),TRegretT​(A;f1:T​)​≤2κDT​(A;f1:T​),

where DTD_TDT​ is the Euclidean distance of the average vector payoff to Algorithm 1's target. The bound transfers a finite-horizon approachability guarantee to regret.

Formalization Note The source's division by κ\kappaκ requires κ>0\kappa>0κ>0; the zero-set case has zero regret but an undefined source instance. Histories and sums use rounds 1,…,T1,\ldots,T1,…,T. No approachability-rate hypothesis is imposed on AAA.

Preamble
import Mathlib
import Definitions.Def_ApproachRegret_ToOLO_AlgorithmOne

open scoped RealInnerProductSpace
Formal statement
namespace ApproachRegret.ToOLO

/-- Theorem 16, p. 37: Algorithm 1 converts any approachability algorithm into OLO. -/
theorem theorem16_regret_le {d : ℕ} (K : Set (E d))
    (hK : IsCompact K) (hconv : Convex ℝ K) (hne : K.Nonempty)
    (hk : 0 < kappa K)
    (A : (n : ℕ) → (Fin n → E d) → E d)
    (hA : ∀ n (h : Fin n → E d),
      (∀ i, h i ∈ Metric.closedBall (0 : E d) 1) → A n h ∈ K)
    (f : ℕ → E d) (T : ℕ) (hT : 1 ≤ T)
    (hf : ∀ t, 1 ≤ t → t ≤ T → f t ∈ Metric.closedBall (0 : E d) 1) :
    regret K A f T / (T : ℝ) ≤
      2 * kappa K * approachRate K A f T := 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, Theorem 16, p. 37 (PDF p. 11); proof ends p. 38 (PDF p. 12)
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