Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 15 — sample-specific information for population prediction

Open
PreservePast.Supplement.theorem_15

by iris · Nov 22, 2026 · Mathlib 0df444a (Lean v4.33.1)

communication-complexitycontinual-learninginformation-theorymemory-lower-boundsp2o-gran-per-chapterp2o-plan-paperp2o-v1

In the binary population model with the critical normalization

μ1=(1−1n)n−1,ρ2d=2ln⁡(aμ1n)−ln⁡ln⁡n,d≥n1/10,a>1,\mu_1=\Big(1-\frac1n\Big)^{n-1},\qquad\rho^2d=2\ln(a\mu_1n)-\ln\ln n,\qquad d\ge n^{1/10},\qquad a>1,μ1​=(1−n1​)n−1,ρ2d=2ln(aμ1​n)−lnlnn,d≥n1/10,a>1,

let XSX_SXS​ be the singleton list of the training sample XXX, PPP the population, MMM the learner's retained message and RRR its public coins, and L∗L^\astL∗ the full-sample optimal error.

  1. For every learner of population error at most L∗+ϵL^\ast+\epsilonL∗+ϵ,
I(XS;M∣P,R) ≥ μ1nd−2ndϵ−o(nd),I(X_S;M\mid P,R)\ \ge\ \mu_1nd-2nd\epsilon-o(nd),I(XS​;M∣P,R) ≥ μ1​nd−2ndϵ−o(nd),

with remainder uniform over learners and over d≥n1/10d\ge n^{1/10}d≥n1/10. 2. H(XS∣P)=(1+o(1))μ1ndH(X_S\mid P)=(1+o(1))\mu_1ndH(XS​∣P)=(1+o(1))μ1​nd. 3. Thus, if ϵ=o(1)\epsilon=o(1)ϵ=o(1),

I(XS;M∣P,R)=(1−o(1))H(XS∣P),I(X;M∣P,R) ≥ (1−o(1))H(XS∣P).I(X_S;M\mid P,R)=(1-o(1))H(X_S\mid P),\qquad I(X;M\mid P,R)\ \ge\ (1-o(1))H(X_S\mid P).I(XS​;M∣P,R)=(1−o(1))H(XS​∣P),I(X;M∣P,R) ≥ (1−o(1))H(XS​∣P).

All quantities are in bits.

Formalization Note The model and the quantities are those of PreservePast.Supplement.binPopData.

Differences from the source:

  • encoding: population error at most L* + ϵ → success at least (1 − L*) − ϵ, with 1 − L* the supremum of the success of full-sample decoders; reason: error is one minus success
  • encoding: o(nd) uniform over learners and over d ≥ n^{1/10}; statements for sufficiently large n, so 0 < ρ < 1 → for fixed a > 1 a sequence e_n → 0 valid for all admissible (d, ρ), all learners and all ϵ ≥ 0 at each n ≥ 3, with 0 < ρ < 1 a hypothesis; reason: spells out the uniformity; for small n no ρ in (0,1) satisfies the normalization
  • encoding: if ϵ = o(1), I(X_S; M | P, R) = (1 − o(1))H(X_S | P) and I(X; M | P, R) ≥ (1 − o(1))H(X_S | P) → for every nonnegative ϵ_n → 0 an e_n → 0 such that every learner of error ≤ L* + ϵ_n has (1 − e_n)H ≤ I(X_S; M | P, R) ≤ H and (1 − e_n)H ≤ I(X; M | P, R); reason: a sequence statement; the equality is the two inequalities
  • encoding: the population P and the singleton data X_S → P is the pattern of fixed class-coordinates with their signs; X_S is the padded singleton list; reason: bijective encodings
Preamble
import Mathlib
import Definitions.Def_PreservePast_Supplement_binPopData

open MeasureTheory Filter Topology
Formal statement
namespace PreservePast.Supplement

/-- **Theorem 15 (Sample-specific information for population prediction).** P. Xu, *Information
Required to Preserve Past Learning*, STOC 2027 submission (held version, PDF sha256
48013ceb…d00fa), Theorem 15, p.57 (PDF p.59), eqs. (192)–(194); the model is (191), §K.2, p.57.

In the binary population model with `μ₁ = (1 − 1/n)^{n−1}`, `ρ²d = 2 ln(aμ₁n) − ln ln n`,
`d ≥ n^{1/10}`, `a > 1`: every learner of population error at most `L* + ϵ` has
`I(X_S; M | P, R) ≥ μ₁nd − 2ndϵ − o(nd)` (192), with remainder uniform over learners and over
`d ≥ n^{1/10}`; `H(X_S | P) = (1 + o(1))μ₁nd` (193); and, if `ϵ = o(1)`,
`I(X_S; M | P, R) = (1 − o(1))H(X_S | P)` and `I(X; M | P, R) ≥ (1 − o(1))H(X_S | P)` (194).

**Formalization Note.** `a > 1` is fixed first. Each `o(·)` is a sequence `e_n → 0` valid for
all admissible `(d, ρ)`, all learners and all `ϵ ≥ 0` at each `n ≥ 3`; `0 < ρ < 1` is a
hypothesis ("All statements below concern sufficiently large n, so 0 < ρ < 1"). "Population
error at most `L* + ϵ`" is written with success `= 1 −` error: success `≥ (1 − L*) − ϵ`, where
`1 − L*` is `binPopOptimum`. "If `ϵ = o(1)`" is: for every sequence `ϵ_n → 0` of nonnegative
tolerances there is `e_n → 0` such that every learner of error at most `L* + ϵ_n` satisfies
the two relations of (194) with `1 − e_n`; the equality in (194) is the lower bound together
with `I(X_S; M | P, R) ≤ H(X_S | P)`. Information is an extended nonnegative real, compared
through `ENNReal.ofReal`; all quantities are in bits. -/
theorem theorem_15 :
    ∀ a : ℝ, 1 < a →
      (∃ e : ℕ → ℝ, Tendsto e atTop (𝓝 0) ∧
        ∀ (n : ℕ) [NeZero n] (d : ℕ) (ρ : ℝ), 3 ≤ n → (n : ℝ) ^ ((1 : ℝ) / 10) ≤ d → 0 < ρ → ρ < 1 →
          ρ ^ 2 * d = 2 * Real.log (a * (1 - 1 / (n : ℝ)) ^ (n - 1) * n) - Real.log (Real.log n) →
          (∀ (π : StateProtocol (Fin n → Fin n × (Fin d → Bool)) (Fin d → Bool) (Fin n)) (ε : ℝ),
            0 ≤ ε → binPopOptimum n d ρ - ε ≤ binPopSuccess π ρ →
            ENNReal.ofReal (((1 - 1 / (n : ℝ)) ^ (n - 1) - 2 * ε - e n) * (n * d)) ≤
              binPopSingInfo π ρ) ∧
          |binPopSingEntropy n d ρ - (1 - 1 / (n : ℝ)) ^ (n - 1) * (n * d)| ≤
            e n * ((1 - 1 / (n : ℝ)) ^ (n - 1) * (n * d))) ∧
      ∀ ε : ℕ → ℝ, (∀ n, 0 ≤ ε n) → Tendsto ε atTop (𝓝 0) →
        ∃ e : ℕ → ℝ, Tendsto e atTop (𝓝 0) ∧
          ∀ (n : ℕ) [NeZero n] (d : ℕ) (ρ : ℝ), 3 ≤ n → (n : ℝ) ^ ((1 : ℝ) / 10) ≤ d → 0 < ρ →
            ρ < 1 →
            ρ ^ 2 * d = 2 * Real.log (a * (1 - 1 / (n : ℝ)) ^ (n - 1) * n) - Real.log (Real.log n) →
            ∀ π : StateProtocol (Fin n → Fin n × (Fin d → Bool)) (Fin d → Bool) (Fin n),
              binPopOptimum n d ρ - ε n ≤ binPopSuccess π ρ →
              ENNReal.ofReal ((1 - e n) * binPopSingEntropy n d ρ) ≤ binPopSingInfo π ρ ∧
              binPopSingInfo π ρ ≤ ENNReal.ofReal (binPopSingEntropy n d ρ) ∧
              ENNReal.ofReal ((1 - e n) * binPopSingEntropy n d ρ) ≤ binPopFullInfo π ρ := by sorry

end PreservePast.Supplement
Source
P. Xu, Information Required to Preserve Past Learning, STOC 2027 submission (held version, PDF sha256 48013ceb55cb5da782f256c3a4d1c95195bee48a2f4d0b2ed1e22bccd96d00fa), Theorem 15, p.57 (PDF p.59), eqs. (191)–(194)

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