Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 1, p. 11 — Algorithm 1 has regret at most C₁√(NT log NT) + C₂N log² NT

Proved
MNLBandit.UCB.theorem_1

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

assortment-optimizationmnl-banditp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1regretupper-confidence-bound

Performance bound for Algorithm 1. There are absolute constants C1C_1C1​ and C2C_2C2​ with the following property. Consider any instance of the MNL-Bandit problem:

  1. NNN products with revenues ri∈[0,1]r_i\in[0,1]ri​∈[0,1];
  2. MNL parameters 0≤vi≤v0=10\le v_i\le v_0=10≤vi​≤v0​=1 (Assumption 4.1.1);
  3. a nonempty feasible family S\mathcal SS of the form (2.3), {S:A x(S)≤b}\{S : A\,x(S)\le b\}{S:Ax(S)≤b} with AAA totally unimodular and bbb integral, closed under taking subsets (Assumption 4.1.2).

Let π\piπ be Algorithm 1 run with any argmax tie-breaking rule. Then for every horizon TTT,

Regπ(T,v)=T R(S∗,v)−Eπ[∑t=1TR(St,v)]≤C1NTlog⁡NT+C2Nlog⁡2NT.\mathrm{Reg}_\pi(T,v)=T\,R(S^*,v)-\mathbb E_\pi\Big[\sum_{t=1}^TR(S_t,v)\Big]\le C_1\sqrt{NT\log NT}+C_2N\log^2NT .Regπ​(T,v)=TR(S∗,v)−Eπ​[t=1∑T​R(St​,v)]≤C1​NTlogNT​+C2​Nlog2NT.

The algorithm does not know vvv: it uses only the revenues, the feasible family and the observed choices. The bound holds without any separation between the optimal and the suboptimal assortments.

Formalization Note. The constants are quantified before every other object (number of products, horizon, parameters, revenues, family and tie-breaking rule), so they are uniform as the page says. log⁡\loglog is the natural logarithm. At NT≤1NT\le1NT≤1 the right side is 000, and so is the regret (with one product and one customer the first assortment is already optimal). The nonemptiness of S\mathcal SS is presupposed by the paper's S∗=argmax⁡S∈SR(S,v)S^*=\operatorname{argmax}_{S\in\mathcal S}R(S,v)S∗=argmaxS∈S​R(S,v).

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 theorem_1 :
    ∃ C₁ C₂ : ℝ, ∀ (N : ℕ) (v r : Fin N → ℝ) (𝒮 : Finset (Finset (Fin N)))
      (hne : 𝒮.Nonempty) (sel : (Finset (Fin N) → ℝ) → Finset (Fin N)) (T : ℕ),
      IsTU 𝒮 → DownClosed 𝒮 → IsArgmaxSel 𝒮 sel →
      (∀ i, 0 ≤ v i) → (∀ i, v i ≤ 1) → (∀ i, r i ∈ Set.Icc (0 : ℝ) 1) →
      regret v r 𝒮 hne (alg1 r sel) T ≤
        C₁ * Real.sqrt (N * T * Real.log (N * T)) + C₂ * N * Real.log (N * T) ^ 2 := by sorry

end MNLBandit.UCB
Source
Agrawal, Avadhanula, Goyal, Zeevi, MNL-Bandit: A Dynamic Learning Approach to Assortment Selection, arXiv:1706.03880v2, p. 11, Theorem 1 and Assumption 4.1
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