Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

Lemma 18 — an explicit solution of c1x≥log⁡(c2xα)c_1x\ge\log(c_2x^\alpha)c1​x≥log(c2​xα)

Proved
OptimalBAI.TrackStop.lambert_inversion

by mikedeng1 · Sep 28, 2026 · Mathlib 0df444a (Lean v4.33.1)

inequalitylambert-wp2o-batch-p200bp2o-gran-per-chapterp2o-plan-paperp2o-v1real-analysis

Let α∈[1,e/2]\alpha\in[1,e/2]α∈[1,e/2] and let c1,c2>0c_1,c_2>0c1​,c2​>0 be constants with c2/c1α>1c_2/c_1^\alpha>1c2​/c1α​>1. If

x=αc1[log⁡(c2ec1α)+log⁡log⁡(c2c1α)]x=\frac{\alpha}{c_1}\left[\log\left(\frac{c_2e}{c_1^\alpha}\right)+\log\log\left(\frac{c_2}{c_1^\alpha}\right)\right]x=c1​α​[log(c1α​c2​e​)+loglog(c1α​c2​​)]

is positive, then

c1x≥log⁡(c2xα).c_1x\ge\log\big(c_2x^\alpha\big).c1​x≥log(c2​xα).

The lemma inverts the inequality c1x≥log⁡(c2xα)c_1x\ge\log(c_2x^\alpha)c1​x≥log(c2​xα) up to the constant α\alphaα, as bounds on the Lambert WWW function do; it converts the threshold log⁡(r(t)/δ)\log(r(t)/\delta)log(r(t)/δ) into an explicit time after which Chernoff's rule has stopped.

Formalization Note The paper states the lemma for all c1,c2>0c_1,c_2>0c1​,c2​>0. Two hypotheses are added so that the printed expressions are defined: c2/c1α>1c_2/c_1^\alpha>1c2​/c1α​>1 (otherwise log⁡log⁡(c2/c1α)\log\log(c_2/c_1^\alpha)loglog(c2​/c1α​) is the logarithm of a non-positive number) and x>0x>0x>0 (otherwise xαx^\alphaxα is undefined; x≤0x\le0x≤0 happens for c2/c1αc_2/c_1^\alphac2​/c1α​ slightly above 111). Every use in the paper has c2/c1α→∞c_2/c_1^\alpha\to\inftyc2​/c1α​→∞.

Preamble
import Mathlib
Formal statement
namespace OptimalBAI.TrackStop

/-- Lemma 18 (Garivier–Kaufmann, arXiv:1602.04589v2, p. 27). For `α ∈ [1, e/2]` and constants
`c₁, c₂ > 0`, the number
`x = (α/c₁) [log(c₂ e / c₁^α) + log log(c₂ / c₁^α)]` satisfies `c₁ x ≥ log(c₂ x^α)`.
Two hypotheses are added so that the printed expressions are defined: `c₂ / c₁^α > 1` (so that
`log log(c₂/c₁^α)` is the logarithm of a positive number) and `x > 0` (so that `x^α` is defined). -/
theorem lambert_inversion (α : ℝ) (hα : α ∈ Set.Icc (1 : ℝ) (Real.exp 1 / 2))
    (c₁ c₂ : ℝ) (hc₁ : 0 < c₁) (hc₂ : 0 < c₂) (hy : c₁ ^ α < c₂)
    (x : ℝ)
    (hx : x = α / c₁ * (Real.log (c₂ * Real.exp 1 / c₁ ^ α) + Real.log (Real.log (c₂ / c₁ ^ α))))
    (hx_pos : 0 < x) :
    Real.log (c₂ * x ^ α) ≤ c₁ * x := by sorry

end OptimalBAI.TrackStop
Source
Garivier, Kaufmann, Optimal Best Arm Identification with Fixed Confidence, arXiv:1602.04589v2, p. 27, Lemma 18
Human review
  • Endorsed by Shuze Chen · Oct 1, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 1, 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 paper
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me