Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 6.1 — Matching lower bound for randomized predictors

Open
CalibratedMA.Randomized.Supplement.theorem_6_1

by mikedeng1 · Nov 15, 2026 · Mathlib 0df444a (Lean v4.33.1)

calibrationmultiaccuracyp2o-batch-stoc27sp2o-gran-per-chapterp2o-plan-paperp2o-v1sample-complexity

Let DDD be the labeled law and CMAD=max⁡{MAD,ECED}\mathrm{CMA}_D=\max\{\mathrm{MA}_D,\mathrm{ECE}_D\}CMAD​=max{MAD​,ECED​} the published error of a full predictor. Probabilities include the iid training sample and an independent training seed; a randomized output may have arbitrary, including continuous, prediction laws.

There are positive universal c,c0,ε0c,c_0,\varepsilon_0c,c0​,ε0​. For every integer NG≥2N_G\ge2NG​≥2 and every 0<ε<ε00<\varepsilon<\varepsilon_00<ε<ε0​, suppose one learner family with common sample count nnn has the following guarantee for every finite discrete domain XXX, every finite bounded test family G⊆[−1,1]XG\subseteq[-1,1]^XG⊆[−1,1]X with ∣G∣≤NG|G|\le N_G∣G∣≤NG​, and every labeled law DDD on X×[0,1]X\times[0,1]X×[0,1]:

Pr⁡{CMAD(Q;G)≤cε}≥2/3.\Pr\{\mathrm{CMA}_D(Q;G)\le c\varepsilon\}\ge2/3.Pr{CMAD​(Q;G)≤cε}≥2/3.

Then the full sum lower bound holds:

n≥c0(log⁡NGε2+1ε5/2).n\ge c_0\left(\frac{\log N_G}{\varepsilon^2}+\frac1{\varepsilon^{5/2}}\right).n≥c0​(ε2logNG​​+ε5/21​).

The learner may depend on the public domain and tests but cannot depend on DDD. This companion theorem matches the two randomized rates; it is not used in the proof of Theorem 4.1.

Differences from the source:

  • encoding: a finite discrete domain [R] → Fin R, with source coordinate i represented by i.val+1; reason: finite relabeling preserves every statistical experiment, test and error
  • encoding: labels in [0,1] or in {0,1} → real labels with the corresponding almost-sure support predicate; reason: the measures are the same labeled laws
  • encoding: an algorithm using iid examples and independent training randomness → a data-and-seed evaluation map, its product training law, and a measurable success event; reason: this gives the stated ordinary probability and keeps the same algorithm for every unknown distribution; invalid-label inputs can be measurably clipped without affecting any instance
  • encoding: sufficiently small positive accuracy → one positive universal ε₀ quantified before all instance parameters; reason: the source proof supplies a threshold uniform in the class budget
  • encoding: one algorithm uniform over finite domains and public test families → one dependent family L R G with common n, chosen before all distributions; reason: finite discrete relabeling preserves all guarantees and permits different public-parameter seed laws
Preamble
import Mathlib
import Definitions.Def_CalibratedMA_Randomized_Supplement_Hidden

open MeasureTheory
Formal statement
namespace CalibratedMA.Randomized.Supplement

/-- Theorem 6.1, p.32: finite domains are represented by their cardinality and relabeling. -/
theorem theorem_6_1 :
    ∃ c c₀ ε₀ : ℝ, 0 < c ∧ 0 < c₀ ∧ 0 < ε₀ ∧
      ∀ NG : ℕ, 2 ≤ NG → ∀ ε : ℝ, 0 < ε → ε < ε₀ →
      ∀ (n : ℕ) (L : ∀ R : ℕ, Finset (Fin R → ℝ) → RandomizedLearner (Fin R) n),
        (∀ (R : ℕ) (G : Finset (Fin R → ℝ)), G.card ≤ NG →
          (∀ g ∈ G, ∀ i, g i ∈ Set.Icc (-1 : ℝ) 1) →
          ∀ D : Measure (Fin R × ℝ), IsLabeledDist D →
            RandomizedSuccess (L R G) D G (c * ε) (2 / 3)) →
        (n : ℝ) ≥ c₀ * (Real.log NG / ε ^ 2 + 1 / ε ^ (5 / 2 : ℝ)) := by sorry

end CalibratedMA.Randomized.Supplement
Source
Jiuyao Lu, Georgy Noarov, Aaron Roth, Calibrated Multiaccuracy: Deterministic and Randomized Sample Complexity, STOC 2027 submission #900 (October 2026; title page November 2, 2026), p. 32, Theorem 6.1 (PDF pp. 34)

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