Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 4.1, p. 13 — v^UCB_{i,ℓ} ≥ vᵢ w.p. ≥ 1 − 6/(Nℓ), and its convergence rate w.p. ≥ 1 − 7/(Nℓ)

Proved
MNLBandit.UCB.lemma_4_1

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

concentration-inequalitymnl-banditp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1upper-confidence-bound

Consider the MNL-Bandit with NNN products, parameters 0≤vi≤v0=10\le v_i\le v_0=10≤vi​≤v0​=1, revenues ri∈[0,1]r_i\in[0,1]ri​∈[0,1], a feasible family S\mathcal SS given by totally unimodular constraints and closed under subsets, and Algorithm 1 with any argmax tie-breaking rule. Let ℓ≥1\ell\ge1ℓ≥1, let iii be a product, and write λℓ=log⁡(Nℓ+1)\lambda_\ell=\log(\sqrt N\ell+1)λℓ​=log(N​ℓ+1). For every horizon TTT, with probabilities restricted to histories in which epoch ℓ\ellℓ is completed by customer TTT:

  1. the upper confidence bound is optimistic,
Pπ(vi,ℓUCB<vi)≤6Nℓ;\mathbb P_\pi\big(v^{\mathrm{UCB}}_{i,\ell}<v_i\big)\le\frac{6}{N\ell};Pπ​(vi,ℓUCB​<vi​)≤Nℓ6​;
  1. with C1=72+24C_1=\sqrt{72}+\sqrt{24}C1​=72​+24​ and C2=144C_2=144C2​=144, on the event Ti(ℓ)≥1T_i(\ell)\ge1Ti​(ℓ)≥1,
Pπ(vi,ℓUCB−vi>C1viλℓTi(ℓ)+C2λℓTi(ℓ))≤7Nℓ.\mathbb P_\pi\Big(v^{\mathrm{UCB}}_{i,\ell}-v_i>C_1\sqrt{\frac{v_i\lambda_\ell}{T_i(\ell)}}+C_2\frac{\lambda_\ell}{T_i(\ell)}\Big)\le\frac{7}{N\ell}.Pπ​(vi,ℓUCB​−vi​>C1​Ti​(ℓ)vi​λℓ​​​+C2​Ti​(ℓ)λℓ​​)≤Nℓ7​.

Optimism (part 1) drives Lemma 4.2 and the convergence rate (part 2) drives Lemma 4.3.

Formalization Note.

  1. The lemma says "there exist constants C1C_1C1​ and C2C_2C2​"; the values 72+24\sqrt{72}+\sqrt{24}72​+24​ and 144144144 are those its proof establishes (p. 35, last display before Lemma A.3), a disclosed instantiation of the existential.
  2. Part 2 needs Ti(ℓ)≥1T_i(\ell)\ge1Ti​(ℓ)≥1 (the right side divides by it). Part 1 needs no such guard: while Ti(ℓ)=0T_i(\ell)=0Ti​(ℓ)=0 the algorithm keeps vi,ℓUCB=1≥viv^{\mathrm{UCB}}_{i,\ell}=1\ge v_ivi,ℓUCB​=1≥vi​.
  3. Finite horizon TTT and the event "epoch ℓ\ellℓ completed" as in Lemma A.2; uniformity in TTT is the paper's statement.
Preamble
import Mathlib
import Definitions.Def_ChoiceCDLP_MNL_mnlObjective
import Definitions.Def_MNLBandit_UCB_Setting
import Definitions.Def_MNLBandit_UCB_Algorithm1
Formal statement
namespace MNLBandit.UCB

open ChoiceCDLP.MNL

theorem lemma_4_1 {N : ℕ} (v r : Fin N → ℝ)
    (𝒮 : Finset (Finset (Fin N))) (sel : (Finset (Fin N) → ℝ) → Finset (Fin N))
    (hTU : IsTU 𝒮) (hdc : DownClosed 𝒮) (hne : 𝒮.Nonempty) (hsel : IsArgmaxSel 𝒮 sel)
    (hv0 : ∀ i, 0 ≤ v i) (hv1 : ∀ i, v i ≤ 1) (hr : ∀ i, r i ∈ Set.Icc (0 : ℝ) 1)
    (T ℓ : ℕ) (hℓ : 1 ≤ ℓ) (i : Fin N) :
    probT v (alg1 r sel) T (fun h =>
        ℓ ≤ epochsDone r sel h ∧ vUCB r sel h i ℓ < v i) ≤ 6 / (N * ℓ) ∧
    probT v (alg1 r sel) T (fun h =>
        ℓ ≤ epochsDone r sel h ∧ 1 ≤ Tcount r sel h i ℓ ∧
        vUCB r sel h i ℓ - v i >
          (Real.sqrt 72 + Real.sqrt 24)
              * Real.sqrt (v i * Real.log (Real.sqrt N * ℓ + 1) / Tcount r sel h i ℓ)
            + 144 * Real.log (Real.sqrt N * ℓ + 1) / Tcount r sel h i ℓ)
        ≤ 7 / (N * ℓ) := by sorry

end MNLBandit.UCB
Source
Agrawal, Avadhanula, Goyal, Zeevi, MNL-Bandit: A Dynamic Learning Approach to Assortment Selection, arXiv:1706.03880v2, p. 13, Lemma 4.1 (proof pp. 34–35)
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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