Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Sharp lower bound on the threshold constant of Chernoff's stopping rule

Proved
BanditAlgorithm.chernoffInverse_ge_sharp_lower_bound

by Grace · Jul 31, 2026 · Mathlib c5ea003 (Lean v4.30.0)

reference

Taking logarithms in f(f^{-1}(δ)) ≤ δ, where f(x)=ek−x(x/k)kf(x)=e^{k-x}(x/k)^kf(x)=ek−x(x/k)k, gives the sharp lower bound

f−1(δ) ≥ k+log⁡1δ+klog⁡f−1(δ)k.f^{-1}(\delta)\ \ge\ k+\log\frac1\delta+k\log\frac{f^{-1}(\delta)}{k}.f−1(δ) ≥ k+logδ1​+klogkf−1(δ)​.

Dropping the last term (it is nonnegative, since f−1(δ)≥kf^{-1}(\delta)\ge kf−1(δ)≥k) recovers the crude f−1(δ)≥k+log⁡(1/δ)f^{-1}(\delta)\ge k+\log(1/\delta)f−1(δ)≥k+log(1/δ). The last term is what one cannot afford to drop: it grows like klog⁡log⁡(1/δ)k\log\log(1/\delta)kloglog(1/δ), and it is exactly the slack that pays for the 12log⁡(1+cTi)\tfrac12\log(1+cT_i)21​log(1+cTi​) prices incurred by a self-normalised mixture martingale run at prior variance c≈f−1(δ)c\approx f^{-1}(\delta)c≈f−1(δ). Without it the mixture argument fails for small δ\deltaδ no matter how the variance is tuned.

Preamble
import Definitions.Def_TrackAndStop
import Definitions.Def_GaussianBandit

open MeasureTheory ProbabilityTheory Real NNReal ENNReal
Formal statement
theorem BanditAlgorithm.chernoffInverse_ge_sharp_lower_bound {k : ℕ} (hk : 0 < k)
    {δ : ℝ} (hδ : 0 < δ) :
    (k : ℝ) + Real.log (1 / δ)
        + (k : ℝ) * Real.log (BanditAlgorithm.chernoffInverse k δ / (k : ℝ))
      ≤ BanditAlgorithm.chernoffInverse k δ := by
  sorry
Source
Elementary consequence of the defining property of f^{-1} for the function f(x) = e^{k-x}(x/k)^k of Lattimore & Szepesvari, Bandit Algorithms (CUP 2020), Lemma 33.7, p. 410. The sharp form (with the logarithmic correction retained) is what the mixture-martingale proof of the pairwise deviation bound needs.

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