Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 6.1 — one-bit feedback achieves O(T3/5log⁡5T)O(T^{3/5}\log^5T)O(T3/5log5T) regret for independent regular valuations

Proved
BilateralProfitRegular.theorem_6_1_regret_bound

by iris · Nov 13, 2026 · Mathlib 0df444a (Lean v4.33.1)

bilateral-tradeonline-learningp2o-gran-per-chapterp2o-plan-paperp2o-v1posted-pricesregret-boundsregular-distributions

There exist a learning algorithm A\mathcal AA with one-bit feedback and a constant CCC such that, for every horizon T≥2T\ge2T≥2 and every pair D\mathcal DD of independent regular seller and buyer distributions on [0,1][0,1][0,1] with strictly positive densities,

RT(A,D)=sup⁡(p,q)∈[0,1]2∑t=1TE[Profitt(p,q)−Profitt(pt,qt)]≤C T3/5log⁡5T.R_T(\mathcal A,\mathcal D)=\sup_{(p,q)\in[0,1]^2}\sum_{t=1}^T\mathbb E\big[\mathrm{Profit}_t(p,q)-\mathrm{Profit}_t(p_t,q_t)\big]\le C\,T^{3/5}\log^5 T .RT​(A,D)=(p,q)∈[0,1]2sup​t=1∑T​E[Profitt​(p,q)−Profitt​(pt​,qt​)]≤CT3/5log5T.

The expectation is over the i.i.d. valuations and the algorithm's randomness. The learner sees only the trade bit of each round. The comparator ranges over all of [0,1]2[0,1]^2[0,1]2, including p>qp>qp>q. The paper's proof gives the sharper O(T3/5log⁡7/2T)O(T^{3/5}\log^{7/2}T)O(T3/5log7/2T). Together with Theorem 7.1's Ω(T3/5)\Omega(T^{3/5})Ω(T3/5) lower bound, the rate for regular distributions is Θ~(T3/5)\tilde\Theta(T^{3/5})Θ~(T3/5).

Formalization Note The algorithm is a family of policies indexed by the horizon, on one seed space, chosen with CCC before TTT and D\mathcal DD. Logarithms are natural.

Differences from the source:

  • reading: "a learning algorithm A\mathcal AA … for every TTT" → a family (πT)T(\pi_T)_T(πT​)T​ of one-bit policies on one seed space, chosen (with CCC) before TTT and the distributions; reason: the paper's algorithms take the horizon as input (Algorithms 7–8; "we choose η\etaη as a function of TTT", p.37)
  • encoding: RT≤O(T3/5log⁡5(T))R_T\le O(T^{3/5}\log^5(T))RT​≤O(T3/5log5(T)) → ∃C>0\exists C>0∃C>0 with the bound C T3/5(log⁡T)5C\,T^{3/5}(\log T)^5CT3/5(logT)5 for every T≥2T\ge2T≥2; reason: at T=1T=1T=1 the right side is 000; O(⋅)O(\cdot)O(⋅) is asymptotic in TTT
  • encoding: sup⁡(p,q)∈[0,1]2\sup_{(p,q)\in[0,1]^2}sup(p,q)∈[0,1]2​ of the expected regret; the learner's randomness → the bound for every comparator in [0,1]2[0,1]^2[0,1]2; a seed drawn once from a probability space, valuations i.i.d. D\mathcal DD independent of it; rounds 0,…,T−10,\dots,T-10,…,T−1; natural log; reason: a supremum is at most BBB iff every term is; standard model of a randomized policy
  • encoding: independent regular seller and buyer distributions on [0,1][0,1][0,1] with strictly positive densities (§2, §6) → RegularUnit E for a published Environment E (supports [0,1][0,1][0,1], E.Regular); PPP, μ\muμ from the joint law E.prior, Fs,FbF_s,F_bFs​,Fb​ = E.cdfS, E.cdfB; reason: the same class: Definitions 2.1–2.2 with the standing positivity of the densities; the valuation laws are the environment's
Preamble
import Mathlib
import Definitions.Def_BilateralProfitRegular_Stochastic
Formal statement
namespace BilateralProfitRegular

open MeasureTheory MechanismDesign.BilateralTrade

/-- **Theorem 6.1 (Regret for regular distributions)**, Brüstle, di Gregorio, Fusco, Leonardi
(manuscript, sha256 e91e8127…), p.36 (PDF 38); proof pp.46–49 (PDF 48–51). There exists a learning
algorithm `𝒜` with one-bit feedback such that, for every `T` and every pair `𝒟` of independent
regular buyer and seller distributions on `[0, 1]` with strictly positive densities,
`R_T(𝒜, 𝒟) ≤ O(T^{3/5} log⁵(T))`.

**Formalization Note.**
* The algorithm is a horizon-indexed family `π T` of randomized one-bit policies on one seed
  space `(Ω, P)`, chosen (with the constant `C`) before `T` and the distributions: the paper's
  algorithms take the horizon `T` as input (Algorithms 7–8; `η` is chosen as a function of `T`).
* `O(·)` is a universal constant `C` for all `T ≥ 2` (at `T = 1` the right side is `0`).
* `R_T = sup_{(p,q) ∈ [0,1]²} ∑_t (E[Profit_t(p, q)] − E[Profit_t(p_t, q_t)])`; the bound is
  stated for every comparator in `[0,1]²`, which is equivalent.
* The distributions are a published `Environment` with supports `[0, 1]` and `E.Regular`
  (Definitions 2.1–2.2); the valuations are i.i.d. with law `E.prior`, independent of the seed.
  Natural logarithm; rounds `Fin T`. -/
theorem theorem_6_1_regret_bound :
    ∃ C : ℝ, 0 < C ∧
      ∃ (Ω : Type) (_ : MeasurableSpace Ω) (P : Measure Ω) (_ : IsProbabilityMeasure P)
        (π : (T : ℕ) → Policy T Ω),
        (∀ T, (π T).OneBit) ∧
        ∀ T : ℕ, 2 ≤ T → ∀ E : Environment, RegularUnit E →
          ∀ a ∈ Set.Icc (0 : ℝ) 1 ×ˢ Set.Icc (0 : ℝ) 1,
            (π T).regret P E.prior a ≤ C * (T : ℝ) ^ ((3 : ℝ) / 5) * Real.log T ^ 5 := by sorry

end BilateralProfitRegular
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), Theorem 6.1, p.36 (PDF 38); proof §6.4, pp.46–49 (PDF 48–51)
Human review
  • Endorsed by Shuze Chen · Nov 15, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Nov 15, 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