Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§4.2.2 (proof of Theorem 4.1) — telescoping regret bound on the grid

Proved
BilateralProfit.telescoping_bound

by iris · Nov 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

bilateral-tradeonline-learningp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1posted-pricesregret-bounds

Let K≥1K\ge1K≥1 and let C0C_0C0​ be a constant for which the information inequality of Theorem 4.2 holds at resolution KKK. Run Algorithm 1 on a valuation sequence v1,…,vT∈GKv_1,\dots,v_T\in G_Kv1​,…,vT​∈GK​. Then:

  1. every weight vector w1,…,wT+1w_1,\dots,w_{T+1}w1​,…,wT+1​ of every run is a probability vector with entries at least 1/(∣A∣(1+βK))1/(|\mathcal A|(1+\beta K))1/(∣A∣(1+βK)) (the lower-bound condition of Lemma 4.6 holds initially and is preserved by each update (5));
  2. for every comparison price a′∈Aa'\in\mathcal Aa′∈A,
∑t=1TProfit(vt,a′)−E[∑t=1TProfit(vt,at)]≤(C0+2)TK+β E[log⁡wT+1(a′)w1(a′)]≤(C0+2)TK+βlog⁡∣A∣.\sum_{t=1}^T\mathrm{Profit}(v_t,a')-\mathbb E\Big[\sum_{t=1}^T\mathrm{Profit}(v_t,a_t)\Big]\le\frac{(C_0+2)T}K+\beta\,\mathbb E\Big[\log\frac{w_{T+1}(a')}{w_1(a')}\Big]\le\frac{(C_0+2)T}K+\beta\log|\mathcal A| .t=1∑T​Profit(vt​,a′)−E[t=1∑T​Profit(vt​,at​)]≤K(C0​+2)T​+βE[logw1​(a′)wT+1​(a′)​]≤K(C0​+2)T​+βlog∣A∣.

Together with grid rounding and Lemma A.6 this gives the regret bound of Theorem 4.1.

Formalization Note The expectation is the average over the JTJ^TJT draw sequences; wt+1w_{t+1}wt+1​ is the weight vector at index ttt.

Differences from the source:

  • generalization: C0C_0C0​ the universal constant of Theorem 4.2 → any C0C_0C0​ for which Theorem 4.2's inequality holds at this KKK for every ρ\rhoρ; reason: the universal C0C_0C0​ is such a constant
  • encoding: the grid GKG_KGK​ of step size 1/K1/K1/K → hypothesis 0<K0<K0<K; reason: the step size 1/K1/K1/K presupposes K≥1K\ge1K≥1 (Lemma A.6: "for every integer K≥1K\ge1K≥1")
  • reading: the displayed chain (p.23), preceded by "The lower-bound condition on wtw_twt​ of Lemma 4.6 holds initially and is preserved by each update prescribed as in Equation (5)" (p.22) → both as clauses: every w1,…,wT+1w_1,\dots,w_{T+1}w1​,…,wT+1​ of every run is a probability vector with entries ≥1/(∣A∣(1+βK))\ge1/(|\mathcal A|(1+\beta K))≥1/(∣A∣(1+βK)), and the chain; reason: the chain's proof rests on the invariant the page asserts, and stating it keeps Lemma 4.6's hypothesis from being vacuous along the run
  • encoding: the expectation over the learner's randomness; rounds 1,…,T1,\dots,T1,…,T → the uniform average over draw sequences ω:{0,…,T−1}→{0,…,J−1}\omega:\{0,\dots,T-1\}\to\{0,\dots,J-1\}ω:{0,…,T−1}→{0,…,J−1}; wt+1w_{t+1}wt+1​ at index ttt; reason: Algorithm 1's only randomness is the independent uniform j⋆j^\starj⋆ of each OneRound call
Preamble
import Mathlib
import Definitions.Def_BilateralProfit_Algorithm1
Formal statement
namespace BilateralProfit

/-- **The telescoping bound in the proof of Theorem 4.1**, Brüstle, di Gregorio, Fusco, Leonardi
(manuscript, sha256 e91e8127…), §4.2.2, pp.22–23 (PDF 24–25).

Let `C0` be a constant for which the information inequality (Theorem 4.2) holds at resolution
`K`, and run Algorithm 1 on a valuation sequence `v_1, …, v_T ∈ G_K`. Then
1. every weight vector `w_1, …, w_{T+1}` of every run is a probability vector with entries at least
   `1/(|𝒜|(1 + βK))` (the lower-bound condition of Lemma 4.6 "holds initially and is preserved by
   each update prescribed as in Equation (5)");
2. for every comparison price `a′ ∈ 𝒜`,
   `Σ_t Profit(v_t, a′) − E[Σ_t Profit(v_t, a_t)] ≤ (C0 + 2)T/K + β E[log(w_{T+1}(a′)/w_1(a′))]
     ≤ (C0 + 2)T/K + β log|𝒜|`.

**Formalization Note.** `w_{t+1}` is `alg1W … t` (`t = 0, …, T`); the expectation is over the
uniform draws `ω`. -/
theorem telescoping_bound (K : ℕ) (hK : 0 < K) (C₀ : ℝ)
    (hC₀ : ∀ ρ : Grid K × Act K → ℝ, IsDist ρ →
      ∃ a : Act K, gap ρ a - beta K * info ρ a ≤ C₀ / K)
    (T : ℕ) (v : Fin T → Grid K) :
    (∀ ω : Fin T → Fin (Jpar K), ∀ t, t ≤ T →
      IsDist (alg1W K T (fun s => pt K (v s)) ω t) ∧
        ∀ a', wFloor K ≤ alg1W K T (fun s => pt K (v s)) ω t a') ∧
    ∀ a' : Act K,
      ∑ t, profit (pt K (v t)) (pt K a'.1) -
          expectAlg K T (fun ω => ∑ t, profit (pt K (v t))
            (pt K (alg1Act K T (fun s => pt K (v s)) ω t).1)) ≤
        (C₀ + 2) * T / K + beta K * expectAlg K T (fun ω =>
          Real.log (alg1W K T (fun s => pt K (v s)) ω T a' /
            alg1W K T (fun s => pt K (v s)) ω 0 a')) ∧
      (C₀ + 2) * T / K + beta K * expectAlg K T (fun ω =>
          Real.log (alg1W K T (fun s => pt K (v s)) ω T a' /
            alg1W K T (fun s => pt K (v s)) ω 0 a')) ≤
        (C₀ + 2) * T / K + beta K * Real.log (nA K) := by sorry

end BilateralProfit
Source
Brüstle, di Gregorio, Fusco, Leonardi, Regret Bounds for Profit Maximization in Bilateral Trade: Learning the Best Posted-Price Mechanism (manuscript, STOC 2027 submission, sha256 e91e81279505b765c7c96c219d674c0fbbbd6ca47a00da8fe228d498ca25ac87), proof of Theorem 4.1, §4.2.2, pp.22–23 (PDF 24–25)
Human review
  • Endorsed by Shuze Chen · Nov 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Nov 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