Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

Lemma 15 — tracking a cumulated sum of proportions

Proved
OptimalBAI.TrackStop.cumulative_tracking_bound

by mikedeng1 · Sep 28, 2026 · Mathlib 0df444a (Lean v4.33.1)

best-arm-identificationdeterministicp2o-batch-p200bp2o-gran-per-chapterp2o-plan-paperp2o-v1tracking

Let KKK be a positive integer, ΣK\Sigma_KΣK​ the simplex of dimension K−1K-1K−1, and δi\delta_iδi​ the vertex of ΣK\Sigma_KΣK​ with a 111 on coordinate iii. For a positive integer nnn, let p(1),…,p(n)∈ΣKp(1),\dots,p(n)\in\Sigma_Kp(1),…,p(n)∈ΣK​ and P(k)=p(1)+⋯+p(k)P(k)=p(1)+\dots+p(k)P(k)=p(1)+⋯+p(k) for k≤nk\le nk≤n. Let N(0)=0N(0)=0N(0)=0 and, for k∈{0,…,n−1}k\in\{0,\dots,n-1\}k∈{0,…,n−1},

Ik+1∈argmax⁡1≤i≤K[Pi(k+1)−Ni(k)],N(k+1)=N(k)+δIk+1.I_{k+1}\in\operatorname*{argmax}_{1\le i\le K}\big[P_i(k+1)-N_i(k)\big],\qquad N(k+1)=N(k)+\delta_{I_{k+1}}.Ik+1​∈1≤i≤Kargmax​[Pi​(k+1)−Ni​(k)],N(k+1)=N(k)+δIk+1​​.

Then

max⁡1≤i≤K∣Ni(n)−Pi(n)∣≤K−1.\max_{1\le i\le K}\big|N_i(n)-P_i(n)\big|\le K-1.1≤i≤Kmax​​Ni​(n)−Pi​(n)​≤K−1.

The lemma is the deterministic core of C-Tracking: greedily drawing the arm whose count lags most behind the cumulated targets keeps every count within K−1K-1K−1 of its target.

Formalization Note Arms are indexed 0,…,K−10,\dots,K-10,…,K−1; the sequence ppp keeps the paper's indices 1,…,n1,\dots,n1,…,n, and its other values are ignored.

Preamble
import Mathlib
import Definitions.Def_OptimalBAI_TrackStop_OptimalProportions
Formal statement
namespace OptimalBAI.TrackStop

/-- Lemma 15 (Garivier–Kaufmann, arXiv:1602.04589v2, p. 20). Proportions `p(1), …, p(n) ∈ Σ_K`
with cumulated sums `P(k) = p(1) + ⋯ + p(k)`; `N(0) = 0`, `I_{k+1}` maximizes
`P_i(k+1) - N_i(k)` over `i`, and `N(k+1) = N(k) + δ_{I_{k+1}}`. Then
`max_i |N_i(n) - P_i(n)| ≤ K - 1`. Arms are `Fin K` (the paper's arm `i` is index `i - 1`); the
sequence `p` keeps the paper's 1-based index, and its values outside `1, …, n` are ignored. -/
theorem cumulative_tracking_bound {K : ℕ} (hK : 0 < K) (n : ℕ) (hn : 0 < n)
    (p : ℕ → Fin K → ℝ) (hp : ∀ k, 1 ≤ k → k ≤ n → p k ∈ simplex K)
    (N : ℕ → Fin K → ℝ) (I : ℕ → Fin K)
    (hN0 : N 0 = 0)
    (hI : ∀ k, k < n → ∀ i : Fin K,
      (∑ j ∈ Finset.Icc 1 (k + 1), p j i) - N k i ≤
        (∑ j ∈ Finset.Icc 1 (k + 1), p j (I (k + 1))) - N k (I (k + 1)))
    (hN : ∀ k, k < n → N (k + 1) = N k + Pi.single (I (k + 1)) (1 : ℝ)) :
    ∀ i : Fin K, |N n i - ∑ j ∈ Finset.Icc 1 n, p j i| ≤ (K : ℝ) - 1 := by sorry

end OptimalBAI.TrackStop
Source
Garivier, Kaufmann, Optimal Best Arm Identification with Fixed Confidence, arXiv:1602.04589v2, p. 20, Lemma 15
Human review
  • Endorsed by Shuze Chen · Oct 1, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 1, 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 paper
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me