Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

G.2, display after (G.16), p. 50 (corrected: the claim that f is decreasing is omitted) — f(x) < 2 for large x, and m ≥ 2x(log x)² ⇒ m/(log m)² ≥ x

Proved
OfflineCMC.Minimax.log_sq_step

by mikedeng1 · Oct 24, 2026 · Mathlib 0df444a (Lean v4.33.1)

p2o-batch-pfp2ap2o-correctedp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1real-analysissample-complexity

Let

f(x)=(1+log⁡2log⁡x+2 log⁡log⁡xlog⁡x)2.f(x)=\Big(1+\frac{\log 2}{\log x}+2\,\frac{\log\log x}{\log x}\Big)^2 .f(x)=(1+logxlog2​+2logxloglogx​)2.

Then:

  1. there is a constant ccc such that f(x)<2f(x)<2f(x)<2 for every x>cx>cx>c;
  2. there is a constant c>1c>1c>1 such that for every x>cx>cx>c and every real mmm,
m≥2x(log⁡x)2⟹m(log⁡m)2≥x.m\ge 2x(\log x)^2\quad\Longrightarrow\quad \frac{m}{(\log m)^2}\ge x .m≥2x(logx)2⟹(logm)2m​≥x.

In the proof of Theorem 2 this is applied with x=CT,δx=\mathbb C_{T,\delta}x=CT,δ​ and x=Cζ,δx=\mathbb C_{\zeta,\delta}x=Cζ,δ​. It turns a sample size of order x(log⁡x)2x(\log x)^2x(logx)2 into the inequality m/(log⁡m)2≥xm/(\log m)^2\ge xm/(logm)2≥x that the Bernstein bound of Proposition 3 needs.

Differences from the source:

  • correction: "This is obviously decreasing in xxx" → not stated; reason: false. With L=log⁡xL=\log xL=logx, the derivative of log⁡2/L+2log⁡L/L\log2/L+2\log L/Llog2/L+2logL/L is (2−2log⁡L−log⁡2)/L2(2-2\log L-\log2)/L^2(2−2logL−log2)/L2, which is positive for L<e1−log⁡2/2≈1.92L<e^{1-\log2/2}\approx1.92L<e1−log2/2≈1.92, i.e. for x<6.8x<6.8x<6.8. The claim is not used.
  • generalization: m=2CT,δ(log⁡CT,δ)2m=2\mathbb C_{T,\delta}(\log\mathbb C_{T,\delta})^2m=2CT,δ​(logCT,δ​)2 → every m≥2x(log⁡x)2m\ge2x(\log x)^2m≥2x(logx)2, for every x>cx>cx>c; reason: at m=2x(log⁡x)2m=2x(\log x)^2m=2x(logx)2 this is the page's display with x=CT,δx=\mathbb C_{T,\delta}x=CT,δ​. It extends to larger mmm because m/(log⁡m)2m/(\log m)^2m/(logm)2 is increasing for m≥e2m\ge e^2m≥e2.
Preamble
import Mathlib
Formal statement
namespace OfflineCMC.Minimax

theorem log_sq_step :
    (∃ c : ℝ, ∀ x : ℝ, c < x →
      (1 + Real.log 2 / Real.log x + 2 * (Real.log (Real.log x) / Real.log x)) ^ 2 < 2) ∧
    ∃ c : ℝ, 1 < c ∧ ∀ x : ℝ, c < x → ∀ m : ℝ, 2 * x * Real.log x ^ 2 ≤ m →
      x ≤ m / Real.log m ^ 2 := by sorry

end OfflineCMC.Minimax
Source
Banerjee, Honnappa & Rao, Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity, arXiv:2211.07092v5, p. 50, App. G.2, display after (G.16)
Human review
  • Endorsed by Shuze Chen · Oct 24, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 24, 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