Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Hybrid connected-four-point contraction identity

Open
QAlgorithms.Papers.Independent.Intakenext100.P88.hybrid_four_point

by Gohan · Oct 31, 2026 · Mathlib 0df444a (Lean v4.33.1)

prove2quantum

Consider any hybrid layer at Gaussian initialization. Its incoming quantum outputs are Qaj=⟨Uϕ(a),OjUϕ(a)⟩Q_{a j}=\langle U\phi(a),O_jU\phi(a)\rangleQaj​=⟨Uϕ(a),Oj​Uϕ(a)⟩, with normalized feature states and m>0m>0m>0 real-linearly independent Hermitian observables. The quantum circuit, features and observables may be drawn from an ensemble. Every QajQ_{a j}Qaj​ is measurable and has finite fourth moment under the actual probability law. The classical preactivations are Car=∑j=1mWrjQaj+brC_{a r}=\sum_{j=1}^m W_{rj}Q_{a j}+b_rCar​=∑j=1m​Wrj​Qaj​+br​. All real weights and biases are centered Gaussian, have independent coordinates, are jointly independent of the incoming quantum outputs, and satisfy Var⁡(Wrj)=CW/m\operatorname{Var}(W_{rj})=C_W/mVar(Wrj​)=CW​/m and Var⁡(br)=Cb\operatorname{Var}(b_r)=C_bVar(br​)=Cb​, with CW,Cb≥0C_W,C_b\ge0CW​,Cb​≥0.

Define κC(1,2,3,4)=E[C1C2C3C4]−E[C1C2]E[C3C4]−E[C1C3]E[C2C4]−E[C1C4]E[C2C3]\kappa_C(1,2,3,4)=\mathbb E[C_1C_2C_3C_4]-\mathbb E[C_1C_2]\mathbb E[C_3C_4]-\mathbb E[C_1C_3]\mathbb E[C_2C_4]-\mathbb E[C_1C_4]\mathbb E[C_2C_3]κC​(1,2,3,4)=E[C1​C2​C3​C4​]−E[C1​C2​]E[C3​C4​]−E[C1​C3​]E[C2​C4​]−E[C1​C4​]E[C2​C3​]. In contrast, define Γab,cd(j,k)=Cov⁡(QajQbj,QckQdk)\Gamma_{ab,cd}(j,k)=\operatorname{Cov}(Q_{aj}Q_{bj},Q_{ck}Q_{dk})Γab,cd​(j,k)=Cov(Qaj​Qbj​,Qck​Qdk​), which subtracts only one product of pair moments.

For arbitrary data a,b,c,da,b,c,da,b,c,d and classical coordinates r,s,t,ur,s,t,ur,s,t,u,

κC((a,r),(b,s),(c,t),(d,u))=(CWm)2(δrsδtu∑j,kΓab,cd(j,k)+δrtδsu∑j,kΓac,bd(j,k)+δruδst∑j,kΓad,bc(j,k)).\begin{aligned} \kappa_C((a,r),(b,s),(c,t),(d,u))=\left(\frac{C_W}{m}\right)^2\Bigl(&\delta_{rs}\delta_{tu}\sum_{j,k}\Gamma_{ab,cd}(j,k)\\ &+\delta_{rt}\delta_{su}\sum_{j,k}\Gamma_{ac,bd}(j,k)\\ &+\delta_{ru}\delta_{st}\sum_{j,k}\Gamma_{ad,bc}(j,k)\Bigr). \end{aligned}κC​((a,r),(b,s),(c,t),(d,u))=(mCW​​)2(​δrs​δtu​j,k∑​Γab,cd​(j,k)+δrt​δsu​j,k∑​Γac,bd​(j,k)+δru​δst​j,k∑​Γad,bc​(j,k)).​

All sums run from 111 to mmm. No diagonal-covariance hypothesis is needed for this exact contraction identity. It retains all covariance terms relevant to this architecture.

Preamble
import Definitions.Def_QAlgorithms_Papers_Independent_Intakenext100_P88
Formal statement
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
Source
Representation Learning via Quantum Neural Tangent Kernels, arXiv:2111.04225v3, PDF p. 38, SM Eqs.(197)-(201)
Read-back

What the Lean code literally says, in plain math · gpt-6.1-sol

Let (Ω,μ)(\Omega,\mu)(Ω,μ) be a probability space, DDD any type, RRR a finite type with decidable equality, h,L,mh,L,mh,L,m natural numbers, and CW,CB≥0C_W,C_B\ge0CW​,CB​≥0. Suppose SSS supplies m>0m>0m>0 and, for every w∈Ωw\in\Omegaw∈Ω, a positive dimension hhh, unitary matrices Wl(w)∈Ch×hW_l(w)\in\mathbb C^{h\times h}Wl​(w)∈Ch×h, Hermitian matrices Xl(w)X_l(w)Xl​(w), real parameters θl(w)\theta_l(w)θl​(w), unit vectors ϕw,a\phi_{w,a}ϕw,a​, and Hermitian observables Oj(w)O_j(w)Oj​(w) that are linearly independent over R\mathbb RR as jjj varies. Define Uw=∏l=0L−1Wl(w)exp⁡(iθl(w)Xl(w))U_w=\prod_{l=0}^{L-1}W_l(w)\exp(i\theta_l(w)X_l(w))Uw​=∏l=0L−1​Wl​(w)exp(iθl​(w)Xl​(w)) in increasing index order and qa,j(w)=Re⁡⟨Uwϕw,a,Oj(w)Uwϕw,a⟩q_{a,j}(w)=\operatorname{Re}\langle U_w\phi_{w,a},O_j(w)U_w\phi_{w,a}\rangleqa,j​(w)=Re⟨Uw​ϕw,a​,Oj​(w)Uw​ϕw,a​⟩; assume each qa,jq_{a,j}qa,j​ is measurable and in L4(μ)L^4(\mu)L4(μ). Let ξr,j\xi_{r,j}ξr,j​ and βr\beta_rβr​ be measurable, mutually independent real random variables with Gaussian laws of mean zero and respective variances CW/mC_W/mCW​/m and CBC_BCB​, and assume their entire family is independent of the entire family of quantum outputs qa,jq_{a,j}qa,j​. Write za,r=∑jξr,jqa,j+βrz_{a,r}=\sum_j\xi_{r,j}q_{a,j}+\beta_rza,r​=∑j​ξr,j​qa,j​+βr​, E\mathbb EE for integration against μ\muμ, and δrs=1\delta_{rs}=1δrs​=1 if r=sr=sr=s and 000 otherwise. Define

Cabcdjk=E[qa,jqb,jqc,kqd,k]−E[qa,jqb,j] E[qc,kqd,k].C_{abcd}^{jk} =\mathbb E[q_{a,j}q_{b,j}q_{c,k}q_{d,k}] -\mathbb E[q_{a,j}q_{b,j}]\,\mathbb E[q_{c,k}q_{d,k}].Cabcdjk​=E[qa,j​qb,j​qc,k​qd,k​]−E[qa,j​qb,j​]E[qc,k​qd,k​].

Then, for every a,b,c,d∈Da,b,c,d\in Da,b,c,d∈D and r,s,t,u∈Rr,s,t,u\in Rr,s,t,u∈R,

E[za,rzb,szc,tzd,u]−E[za,rzb,s] E[zc,tzd,u]−E[za,rzc,t] E[zb,szd,u]−E[za,rzd,u] E[zb,szc,t]=(CWm)2(δrsδtu∑j,k=0m−1Cabcdjk+δrtδsu∑j,k=0m−1Cacbdjk+δruδst∑j,k=0m−1Cadbcjk).\begin{aligned} &\mathbb E[z_{a,r}z_{b,s}z_{c,t}z_{d,u}] -\mathbb E[z_{a,r}z_{b,s}]\,\mathbb E[z_{c,t}z_{d,u}]\\ &\quad-\mathbb E[z_{a,r}z_{c,t}]\,\mathbb E[z_{b,s}z_{d,u}] -\mathbb E[z_{a,r}z_{d,u}]\,\mathbb E[z_{b,s}z_{c,t}]\\ &=\left(\frac{C_W}{m}\right)^2 \left( \delta_{rs}\delta_{tu}\sum_{j,k=0}^{m-1}C_{abcd}^{jk} +\delta_{rt}\delta_{su}\sum_{j,k=0}^{m-1}C_{acbd}^{jk} +\delta_{ru}\delta_{st}\sum_{j,k=0}^{m-1}C_{adbc}^{jk} \right). \end{aligned}​E[za,r​zb,s​zc,t​zd,u​]−E[za,r​zb,s​]E[zc,t​zd,u​]−E[za,r​zc,t​]E[zb,s​zd,u​]−E[za,r​zd,u​]E[zb,s​zc,t​]=(mCW​​)2​δrs​δtu​j,k=0∑m−1​Cabcdjk​+δrt​δsu​j,k=0∑m−1​Cacbdjk​+δru​δst​j,k=0∑m−1​Cadbcjk​​.​

Zero variances and L=0L=0L=0 are allowed, with the empty circuit product equal to the identity; m=0m=0m=0 is excluded. If DDD or RRR is empty, the corresponding choices of data or output indices do not exist.

Human review
  • Endorsed by Shuze Chen · Oct 31, 2026

    Confirmed by the moderator at approval.

  • Endorsed by Gohan · Oct 31, 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