Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 4.3, p. 14 — (1 + V(S_{ℓ+1}))(R̃_{ℓ+1}(S_{ℓ+1}) − R(S_{ℓ+1}, v)) ≤ Σᵢ[C₁√(vᵢ log(√Nℓ+1)/Tᵢ(ℓ)) + C₂ log(√Nℓ+1)/Tᵢ(ℓ)] w.p. ≥ 1 − 13/ℓ

Proved
MNLBandit.UCB.lemma_4_3

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

mnl-banditp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1regretupper-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, λℓ=log⁡(Nℓ+1)\lambda_\ell=\log(\sqrt N\ell+1)λℓ​=log(N​ℓ+1), C1=72+24C_1=\sqrt{72}+\sqrt{24}C1​=72​+24​ and C2=144C_2=144C2​=144. Let Sℓ+1S_{\ell+1}Sℓ+1​ be the assortment computed at the end of epoch ℓ\ellℓ and R~ℓ+1\tilde R_{\ell+1}R~ℓ+1​ the optimistic revenue built from v⋅,ℓUCBv^{\mathrm{UCB}}_{\cdot,\ell}v⋅,ℓUCB​. For every horizon TTT, with probabilities restricted to histories in which epoch ℓ\ellℓ is completed by customer TTT and every product of Sℓ+1S_{\ell+1}Sℓ+1​ has Ti(ℓ)≥1T_i(\ell)\ge1Ti​(ℓ)≥1,

(1+∑j∈Sℓ+1vj)(R~ℓ+1(Sℓ+1)−R(Sℓ+1,v))≤∑i∈Sℓ+1(C1viλℓTi(ℓ)+C2λℓTi(ℓ))\Big(1+\sum_{j\in S_{\ell+1}}v_j\Big)\big(\tilde R_{\ell+1}(S_{\ell+1})-R(S_{\ell+1},v)\big)\le\sum_{i\in S_{\ell+1}}\Big(C_1\sqrt{\frac{v_i\lambda_\ell}{T_i(\ell)}}+C_2\frac{\lambda_\ell}{T_i(\ell)}\Big)(1+j∈Sℓ+1​∑​vj​)(R~ℓ+1​(Sℓ+1​)−R(Sℓ+1​,v))≤i∈Sℓ+1​∑​(C1​Ti​(ℓ)vi​λℓ​​​+C2​Ti​(ℓ)λℓ​​)

with probability at least 1−13ℓ1-\frac{13}{\ell}1−ℓ13​. This per-epoch rate is summed over epochs in the proof of Theorem 1.

Formalization Note.

  1. Sum over iii. The page's right-hand side has a free index iii; its proof ((A.11)–(A.12), p. 36) gives the sum over i∈Sℓi\in S_\elli∈Sℓ​, which is stated.
  2. Index reading. As in Lemma 4.2, the page's R~ℓ(Sℓ)\tilde R_\ell(S_\ell)R~ℓ​(Sℓ​) with vi,ℓUCBv^{\mathrm{UCB}}_{i,\ell}vi,ℓUCB​, Ti(ℓ)T_i(\ell)Ti​(ℓ) and 1−13/ℓ1-13/\ell1−13/ℓ is read as the estimate built at the end of epoch ℓ\ellℓ.
  3. Constants. "There exist constants C1C_1C1​ and C2C_2C2​" is instantiated with the values of Lemma 4.1's proof.
  4. Guard. The right side divides by Ti(ℓ)T_i(\ell)Ti​(ℓ), so the event requires Ti(ℓ)≥1T_i(\ell)\ge1Ti​(ℓ)≥1 for every i∈Sℓ+1i\in S_{\ell+1}i∈Sℓ+1​.
  5. Finite horizon TTT as in Lemma A.2.
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_3 {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) :
    probT v (alg1 r sel) T (fun h =>
        ℓ ≤ epochsDone r sel h ∧
        (∀ i ∈ nextSet r sel h ℓ, 1 ≤ Tcount r sel h i ℓ) ∧
        ¬ ((1 + ∑ j ∈ nextSet r sel h ℓ, v j) *
              (mnlObjective (fun j => vUCB r sel h j ℓ) r 1 (nextSet r sel h ℓ)
                - mnlObjective v r 1 (nextSet r sel h ℓ)) ≤
            ∑ i ∈ nextSet r sel h ℓ,
              ((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)))
      ≤ 13 / ℓ := by sorry

end MNLBandit.UCB
Source
Agrawal, Avadhanula, Goyal, Zeevi, MNL-Bandit: A Dynamic Learning Approach to Assortment Selection, arXiv:1706.03880v2, p. 14, Lemma 4.3 (proof p. 36, (A.11)–(A.12))
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