Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma 4, p. 20 — quantization costs at most (2/M + 1/K)T regret

Proved
FirstPriceLearning.Stochastic.lemma_4

by mikedeng1 · Oct 14, 2026 · Mathlib 0df444a (Lean v4.33.1)

first-price-auctionsp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1quantizationregret

Let M,K≥1M,K\ge1M,K≥1, let GGG be any CDF on [0,1][0,1][0,1], let v=(v1,…,vT)∈[0,1]Tv=(v_1,\dots,v_T)\in[0,1]^Tv=(v1​,…,vT​)∈[0,1]T be an arbitrary value sequence and v~t=min⁡{x∈C:x≥vt}\tilde v_t=\min\{x\in\mathcal C:x\ge v_t\}v~t​=min{x∈C:x≥vt​} its clipping to C={1/M,…,1}\mathcal C=\{1/M,\dots,1\}C={1/M,…,1}. Let b1,…,bTb_1,\dots,b_Tb1​,…,bT​ be bids on the grid A={1/K,…,1}\mathcal A=\{1/K,\dots,1\}A={1/K,…,1}: the bids of a policy πQ\pi^{\mathrm Q}πQ of the quantized problem, which the induced policy π\piπ plays in the original problem. Then

RT(π,v) ≤ R~T(πQ,v)+(2M+1K)T,R~T(πQ,v)=∑t=1T(max⁡b∈AR(v~t,b)−R(v~t,bt)),R_T(\pi,v)\ \le\ \tilde R_T(\pi^{\mathrm Q},v)+\Big(\frac2M+\frac1K\Big)T,\qquad \tilde R_T(\pi^{\mathrm Q},v)=\sum_{t=1}^T\Big(\max_{b\in\mathcal A}R(\tilde v_t,b)-R(\tilde v_t,b_t)\Big),RT​(π,v) ≤ R~T​(πQ,v)+(M2​+K1​)T,R~T​(πQ,v)=t=1∑T​(b∈Amax​R(v~t​,b)−R(v~t​,bt​)),

where RT(π,v)R_T(\pi,v)RT​(π,v) is the regret (3), computed with the maximum over all bids in [0,1][0,1][0,1] and the true values.

This is the step that transfers a regret bound for the finite contextual bandit to the continuous auction.

Formalization Note. The statement is pathwise: it holds for every bid sequence on the grid, so it applies to every realization of a randomized πQ\pi^{\mathrm Q}πQ.

Preamble
import Mathlib
import Definitions.Def_FirstPriceLearning_Stochastic_Auction
Formal statement
namespace FirstPriceLearning.Stochastic

open MeasureTheory

/-- Lemma 4 (p. 20): quantization loses at most `(2/M + 1/K) T`. For any value sequence
`v ∈ [0,1]^T`, any HOB law `G` on `[0, 1]` and any bids `b_t` on the grid `𝒜 = {1/K, …, 1}` (the
bids of a policy `π^Q` of the quantized problem, which the induced policy `π` also plays), the
regret (3) is at most the quantized regret `R̃_T(π^Q, v)`, computed against the clipped values
`ṽ_t = min {x ∈ 𝒞 : x ≥ v_t}`, `𝒞 = {1/M, …, 1}`, plus `(2/M + 1/K) T`. -/
theorem lemma_4 (T M K : ℕ) (hM : 1 ≤ M) (hK : 1 ≤ K) (μG : Measure ℝ) [IsProbabilityMeasure μG]
    (hG : μG (Set.Icc (0 : ℝ) 1)ᶜ = 0) (v : Fin T → ℝ) (hv : ∀ t, v t ∈ Set.Icc (0 : ℝ) 1)
    (b : Fin T → ℝ) (hb : ∀ t, b t ∈ gridA K) :
    regret μG v b ≤
      gridRegret μG (gridA K) (fun t => clipValue M (v t)) b + (2 / M + 1 / K) * T := by sorry

end FirstPriceLearning.Stochastic
Source
Han, Zhou, Weissman, Optimal No-regret Learning in Repeated First-price Auctions, arXiv:2003.09795v7, p. 20, Lemma 4
Human review
  • Endorsed by Shuze Chen · Oct 14, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 14, 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