Hybrid connected-four-point contraction identity
OpenQAlgorithms.Papers.Independent.Intakenext100.P88.hybrid_four_pointConsider any hybrid layer at Gaussian initialization. Its incoming quantum outputs are , with normalized feature states and real-linearly independent Hermitian observables. The quantum circuit, features and observables may be drawn from an ensemble. Every is measurable and has finite fourth moment under the actual probability law. The classical preactivations are . All real weights and biases are centered Gaussian, have independent coordinates, are jointly independent of the incoming quantum outputs, and satisfy and , with .
Define . In contrast, define , which subtracts only one product of pair moments.
For arbitrary data and classical coordinates ,
All sums run from to . No diagonal-covariance hypothesis is needed for this exact contraction identity. It retains all covariance terms relevant to this architecture.
import Definitions.Def_QAlgorithms_Papers_Independent_Intakenext100_P88
noncomputable section
namespace QAlgorithms.Papers.Independent.Intakenext100.P88
open scoped BigOperators ComplexConjugate Topology NNReal ComplexOrder
open MeasureTheory ProbabilityTheory Filter
/-- PDF pp.37-38 Eqs.(197)-(201): exact connected-four-point contraction.
The quantum term is product covariance, not the four-variable quantum cumulant.
No orthogonality or diagonal covariance hypothesis is needed for this identity. -/
theorem hybrid_four_point {Ω D R : Type*} [MeasurableSpace Ω] [Fintype R] [DecidableEq R]
(μ : Measure Ω) [IsProbabilityMeasure μ] {h L m : ℕ} {CW CB : ℝ≥0}
(S : HybridLayer μ D R h L m CW CB) (a b c d : D) (r s t u : R) :
connectedFour μ (preactivation S a r) (preactivation S b s)
(preactivation S c t) (preactivation S d u) = fourContraction S a b c d r s t u := by sorry
end QAlgorithms.Papers.Independent.Intakenext100.P88
end
Read-back
What the Lean code literally says, in plain math · gpt-6.1-sol
Let be a probability space, any type, a finite type with decidable equality, natural numbers, and . Suppose supplies and, for every , a positive dimension , unitary matrices , Hermitian matrices , real parameters , unit vectors , and Hermitian observables that are linearly independent over as varies. Define in increasing index order and ; assume each is measurable and in . Let and be measurable, mutually independent real random variables with Gaussian laws of mean zero and respective variances and , and assume their entire family is independent of the entire family of quantum outputs . Write , for integration against , and if and otherwise. Define
Then, for every and ,
Zero variances and are allowed, with the empty circuit product equal to the identity; is excluded. If or is empty, the corresponding choices of data or output indices do not exist.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.