Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 4.12 — R(C)=O(fETD(C)log⁡∣C∣/log⁡(1+fETD(C)))R(C)=O(\mathrm{fETD}(C)\log|C|/\log(1+\mathrm{fETD}(C)))R(C)=O(fETD(C)log∣C∣/log(1+fETD(C)))

Open
ExactLearningSeparation678.Randomized.Supplement.theorem_4_12

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

machine-learningp2o-batch-stoc27sp2o-gran-per-chapterp2o-plan-paperp2o-v1quantum-informationquery-complexity

There is an absolute constant K>0K>0K>0 such that for every concept class C⊆{0,1}NC\subseteq\{0,1\}^NC⊆{0,1}N,

R(C)≤K fETD(C) log⁡∣C∣log⁡(1+fETD(C)),R(C)\le K\,\frac{\mathrm{fETD}(C)\,\log|C|}{\log\big(1+\mathrm{fETD}(C)\big)},R(C)≤Klog(1+fETD(C))fETD(C)log∣C∣​,

where R(C)R(C)R(C) is the randomized query complexity of exactly learning CCC (success probability at least 2/32/32/3 on every target, worst-case number of queries) and fETD(C)\mathrm{fETD}(C)fETD(C) is the fractional extended teaching dimension.

It is a randomized, fractional analogue of the deterministic ETD\mathrm{ETD}ETD upper bound of Hegedűs and Moshkov.

Formalization Note The constant precedes the coordinate set and the class. Logarithms are natural. For ∣C∣≤1|C|\le1∣C∣≤1, fETD(C)=0\mathrm{fETD}(C)=0fETD(C)=0 and the right side is 0/00/00/0, which real division reads as 000; then R(C)=0R(C)=0R(C)=0.

Differences from the source:

  • encoding: coordinates [N] of C ⊆ {0,1}^N → an arbitrary finite type ι : Type with decidable equality, concepts ι → Bool; reason: a relabeling of [N]; every N, including N = 0, is an instance
  • encoding: bounded-error quantum and randomized query complexities Q(C), R(C) → the published quantumExactComplexity (QueryAlg, XOR oracle, any finite workspace) and classicalExactComplexity (randomized decision trees, worst-case query bound), success ≥ 2/3 on every target; reason: the mission’s published models of the source’s Q and R
  • encoding: R(C) = O(fETD(C) log|C| / log(1+fETD(C))) for every C → one K > 0 quantified before ι and C, bounding the worst-case randomized query complexity; reason: the source’s O is uniform over all classes; the bound is on R itself, not on an expected depth
  • encoding: logarithms of unspecified base → natural logarithm Real.log; reason: a change of base is absorbed into the absolute constant
  • encoding: fETD(C,h) minimizes over c* ∈ C and all real nonnegative coordinate weights, then fETD(C) maximizes over every ambient h → fetdAt is the real infimum of the same total-weight objective over feasible pairs (c*, w); fetd is the supremum over all ambient Boolean functions; reason: for C nonempty feasible weights exist and can be clipped to [0,1] without violating any constraint or increasing cost; finitely many c* and compact weight cubes give attainment, and the outer index is finite and nonempty
  • reading: γ and fγ have no feasible optimization point when |C| ≤ 1; fETD has none only when C is empty; the source assigns no value in these cases → empty real infima are 0 and real division by 0 is 0; fETD of a singleton is already 0 using feasible zero weights; reason: this supplies values only for undefined degenerate extrema; every trivial-class clause is true and every source-defined nontrivial instance is retained
Preamble
import Definitions.Def_ExactLearningSeparation678_Randomized_Supplement_Teaching

open Classical
set_option autoImplicit false
Formal statement
namespace ExactLearningSeparation678.Randomized.Supplement

open QAlgorithms.Learning

/-- Theorem 4.12, p.34: `R(C) = O(fETD(C) log |C| / log(1 + fETD(C)))` uniformly: one absolute
`K > 0`, fixed before `N` and `C`, bounds the worst-case randomized exact-learning complexity
for every concept class. Natural logarithms; real division by `0` is `0`. -/
theorem theorem_4_12 : ∃ K : ℝ, 0 < K ∧
    ∀ (ι : Type) [Fintype ι] [DecidableEq ι] (C : Finset (ι → Bool)),
      (classicalExactComplexity C : ℝ) ≤
        K * (fetd C * Real.log (C.card : ℝ) / Real.log (1 + fetd C)) := by sorry

end ExactLearningSeparation678.Randomized.Supplement
Source
Srinivasan Arunachalam, Amin Shiraz Gilani, Nikhil S. Mande, STOC 2027 submission #678 (October 2026), Theorem 4.12, p.34 (proof pp.34–36); https://github.com/sigact-stoc/stoc2027/releases/download/papers-1/678.pdf

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