Deep linear network: (eqs. 3.21–3.24)
ProvedDeepLearningTheory.linearNet_G4_recursionFor a zero-bias deep linear network with positive widths at initialization and a single input , let and suppose the layer- four-point correlator has the Wick tensor structure with coefficient :
Then the layer- correlator has the same structure with
import Mathlib import Definitions.Def_DLT_DeepLinearNetwork open MeasureTheory ProbabilityTheory open scoped NNReal
namespace DeepLearningTheory
theorem linearNet_G4_recursion {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω)
[IsProbabilityMeasure P] (n : ℕ → ℕ) (hn : ∀ ℓ, 0 < n ℓ) (CW : ℝ≥0)
(W : Ω → ℕ → ℕ → ℕ → ℝ) (hW : IsLinearNetInit P n CW W) (x : ℕ → ℝ) (ℓ : ℕ)
(hℓ : 1 ≤ ℓ) (G4 : ℝ)
(hG4 : ∀ i₁ i₂ i₃ i₄, i₁ < n ℓ → i₂ < n ℓ → i₃ < n ℓ → i₄ < n ℓ →
∫ ω, linearPreact n (W ω) x ℓ i₁ * linearPreact n (W ω) x ℓ i₂ *
linearPreact n (W ω) x ℓ i₃ * linearPreact n (W ω) x ℓ i₄ ∂P
= wickDelta4 i₁ i₂ i₃ i₄ * G4)
(i₁ i₂ i₃ i₄ : ℕ) (hi₁ : i₁ < n (ℓ + 1)) (hi₂ : i₂ < n (ℓ + 1))
(hi₃ : i₃ < n (ℓ + 1)) (hi₄ : i₄ < n (ℓ + 1)) :
∫ ω, linearPreact n (W ω) x (ℓ + 1) i₁ * linearPreact n (W ω) x (ℓ + 1) i₂ *
linearPreact n (W ω) x (ℓ + 1) i₃ * linearPreact n (W ω) x (ℓ + 1) i₄ ∂P
= wickDelta4 i₁ i₂ i₃ i₄ * ((CW : ℝ) ^ 2 * (1 + 2 / (n ℓ : ℝ)) * G4) := by sorry
end DeepLearningTheoryRead-back
What the Lean code literally says, in plain math · Aristotle (Harmonic) - non-blind, same agent as the drafter
Non-blind read-back. This read-back was written by the same agent that drafted the Lean statement, with full knowledge of the source text and of the intended meaning. It is not independent testimony and must not be mistaken for a blind audit; reviewers should compare the Lean code against the source themselves.
Let be a probability space, widths with all , , satisfying IsLinearNetInit, an input, and . Assume that for all , . Then for all , . Here is the three-term Kronecker-delta tensor and are the zero-bias linear preactivations. The hypothesis is an assumption on the given (it holds, e.g., with the value from the goal theorem).
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.