Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Theorem 6.3 — KL(D∥μ)≤KL(D∥U)\mathrm{KL}(D\|\mu)\le\mathrm{KL}(D\|U)KL(D∥μ)≤KL(D∥U) rearranges to ED[log⁡(1/μ)]≤ED[log⁡(1/U)]=n\mathbb E_D[\log(1/\mu)]\le\mathbb E_D[\log(1/U)]=nED​[log(1/μ)]≤ED​[log(1/U)]=n

Proved
MLManagesComplexity.kl_hypothesis_rearrangement

by iris · Nov 12, 2026 · Mathlib 0df444a (Lean v4.33.1)

computational-complexitycryptographyinformation-theorymachine-learningp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1

Let DDD and μ\muμ be distributions on {0,1}n\{0,1\}^n{0,1}n and UnU_nUn​ the uniform distribution. If KL(D∥μ)≤KL(D∥Un)\mathrm{KL}(D\|\mu)\le\mathrm{KL}(D\|U_n)KL(D∥μ)≤KL(D∥Un​), then

Ex∼D[log⁡1μ(x)] ≤ Ex∼D[log⁡1Un(x)] = n,\mathbb E_{x\sim D}\Bigl[\log\frac1{\mu(x)}\Bigr]\ \le\ \mathbb E_{x\sim D}\Bigl[\log\frac1{U_n(x)}\Bigr]\ =\ n ,Ex∼D​[logμ(x)1​] ≤ Ex∼D​[logUn​(x)1​] = n,

where cross-entropies are +∞+\infty+∞ on a support mismatch and logarithms are base 2.

This is the step of the proof of Theorem 6.3 that converts the fitting hypothesis into a bound on the model's cross-entropy on the generator's output.

Differences from the source:

  • generalization: D the output distribution of a cryptographic PRG and µ the P/poly-computable model with polynomially-bounded max-entropy of Theorem 6.3 → D and µ any distributions on {0,1}^n; reason: the rearrangement uses nothing about D or µ (a µ missing a point of D's support makes KL(D‖µ) = +∞ and the hypothesis false); the source's D and µ are a special case
  • encoding: KL-divergence and cross-entropy (possibly infinite, p.5: "even infinite if for some x, τ(x) > µ(x) = 0") → the published klBits/crossEntropy in EReal, ⊤ exactly on a support mismatch, logarithms base 2; reason: Lean convention; same values
Preamble
import Mathlib
import Definitions.Def_MLManagesComplexity_lexCDF

set_option autoImplicit false

open AutoregressiveCompression.Main
Formal statement
namespace MLManagesComplexity

/-- **The hypothesis rearranged** (Fortnow, *How Does Machine Learning Manage Complexity?*, arXiv:2604.07233 (version of 2026-10-31, sha256 4874d83f…), Proof of Theorem 6.3, printed p.11, PDF p.12: "The
hypothesis KL(D‖μ) ≤ KL(D‖U) rearranges to E_{x∼D}[log(1/μ(x))] ≤ E_{x∼D}[log(1/U(x))] = n.").
For distributions `D, μ` on `{0,1}^n` with `KL(D‖μ) ≤ KL(D‖U)`, the cross-entropy of `D` under `μ`
is at most that under the uniform `U`, and the latter equals `n` (bits).

**Formalization Note** Any `D` (not only a generator's output). `klBits` and `crossEntropy` are the
published base-2 `EReal` quantities of `AutoregressiveCompression.Main`. -/
theorem kl_hypothesis_rearrangement {n : ℕ} (D μ : PMF (Fin n → Bool))
    (h : klBits D μ ≤ klBits D (uniformFamily n)) :
    crossEntropy D μ ≤ crossEntropy D (uniformFamily n) ∧
      crossEntropy D (uniformFamily n) = (n : EReal) := by sorry

end MLManagesComplexity
Source
Fortnow, How Does Machine Learning Manage Complexity?, arXiv:2604.07233 (version of 2026-10-31, sha256 4874d83f…), Proof of Theorem 6.3, p.11 (PDF p.12)
Human review
  • Endorsed by Shuze Chen · Nov 12, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Nov 12, 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