Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Appendix B.1, p. 33 — r = Ue + (ℰ_v − ℰb) + Y(b − β*) and ‖r‖₂ ≤ ‖Ue‖₂ + ‖ℰ_v − ℰb‖₂ + ‖Y‖₂‖b − β*‖₂

Proved
SynDigits.Ridge.structural_split

by mikedeng1 · Oct 24, 2026 · Mathlib 0df444a (Lean v4.33.1)

error-boundlatent-factor-modelp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1synthetic-control

Consider the latent factor model of §4.1: there are user embeddings U∈Rn×dU \in \mathbb{R}^{n\times d}U∈Rn×d and question embeddings V∈Rm×dV \in \mathbb{R}^{m\times d}V∈Rm×d (rows vjv_jvj​), a noise matrix E∈Rn×m\mathcal E \in \mathbb{R}^{n\times m}E∈Rn×m, and the human responses are Y=UV⊤+EY = UV^\top + \mathcal EY=UV⊤+E. The new question has embedding v∈Rdv \in \mathbb{R}^dv∈Rd and noise Ev∈Rn\mathcal E_v \in \mathbb{R}^nEv​∈Rn, with human responses Yv=Uv+EvY_v = Uv + \mathcal E_vYv​=Uv+Ev​. Decompose v=V⊤b+ev = V^\top b + ev=V⊤b+e with coefficients b∈Rmb \in \mathbb{R}^mb∈Rm and residual e∈Rde \in \mathbb{R}^de∈Rd. For any Σ~∈Rm×m\tilde\Sigma \in \mathbb{R}^{m\times m}Σ~∈Rm×m, γ~∈Rm\tilde\gamma \in \mathbb{R}^mγ~​∈Rm and λ\lambdaλ, let β∗=(Σ~+λI)−1γ~\beta^* = (\tilde\Sigma + \lambda I)^{-1}\tilde\gammaβ∗=(Σ~+λI)−1γ~​ and r=Yv−Yβ∗r = Y_v - Y\beta^*r=Yv​−Yβ∗. Then

r=Ue+(Ev−Eb)+Y(b−β∗),∥r∥2≤∥Ue∥2+∥Ev−Eb∥2+∥Y∥2 ∥b−β∗∥2.r = Ue + (\mathcal E_v - \mathcal E b) + Y(b - \beta^*), \qquad \|r\|_2 \le \|Ue\|_2 + \|\mathcal E_v - \mathcal E b\|_2 + \|Y\|_2\,\|b - \beta^*\|_2 .r=Ue+(Ev​−Eb)+Y(b−β∗),∥r∥2​≤∥Ue∥2​+∥Ev​−Eb∥2​+∥Y∥2​∥b−β∗∥2​.

This splits the structural error of Theorem 4.1 into the part of the new question not representable by the existing ones, the noise, and the distance from bbb to the population Ridge target.

Formalization Note The identity holds for any vector in place of β∗\beta^*β∗, so no invertibility hypothesis is needed here.

Differences from the source:

  • generalization: Σ̃ = (1/n)𝔼[ỸᵀỸ] PSD, γ̃ = (1/n)𝔼[ỸᵀỸ_v], Ridge penalty λ ≥ 0 → any matrix Sig, any vector gam, any real lam (no hypothesis); reason: the step is an algebraic identity plus the triangle inequality and holds for every value, so it specializes to the paper's Σ̃, γ̃, λ
  • encoding: v = Vb + e → v = Vᵀ *ᵥ b + e; reason: V ∈ ℝ^{m×d} has the question embeddings as rows and b ∈ ℝ^m, so only Vᵀb type-checks; the proof's Yb = UVᵀb + ℰb (p. 32) confirms it
  • reading: Y_v = Uv (§4.1, p. 9, noiseless); ℰ_v appears in Theorem 4.1 without a definition → hYv : Yv = U *ᵥ v + Ev; reason: Theorem 4.1 is stated "in the noisy setting" (p. 11) and its proof writes Y_v − Yb = Uv + ℰ_v − UVb − ℰb (p. 32), so Y_v = Uv + ℰ_v; Ev = 0 recovers the noiseless model of p. 9
  • encoding: vectors in ℝⁿ, n×m matrices, ‖·‖₂, spectral norm, σ_min → Fin n → ℝ, Matrix (Fin n) (Fin m) ℝ, vnorm, GaussianMatrix.specNorm, GaussianMatrix.sMin; reason: Lean representation of the same objects; same instances
Preamble
import Mathlib
import Definitions.Def_GaussianMatrix_basic
import Definitions.Def_SynDigits_Ridge_Model
open Matrix GaussianMatrix
Formal statement
namespace SynDigits.Ridge

theorem structural_split {n m d : ℕ} (U : Matrix (Fin n) (Fin d) ℝ)
    (V : Matrix (Fin m) (Fin d) ℝ) (Eps Y : Matrix (Fin n) (Fin m) ℝ) (v e : Fin d → ℝ)
    (Ev Yv : Fin n → ℝ) (b : Fin m → ℝ) (Sig : Matrix (Fin m) (Fin m) ℝ) (gam : Fin m → ℝ)
    (lam : ℝ)
    (hY : Y = U * Vᵀ + Eps) (hYv : Yv = U *ᵥ v + Ev) (hv : v = Vᵀ *ᵥ b + e) :
    resid Y Yv Sig gam lam = U *ᵥ e + (Ev - Eps *ᵥ b) + Y *ᵥ (b - betaStar Sig gam lam) ∧
      vnorm (resid Y Yv Sig gam lam)
        ≤ vnorm (U *ᵥ e) + vnorm (Ev - Eps *ᵥ b)
          + specNorm Y * vnorm (b - betaStar Sig gam lam) := by sorry

end SynDigits.Ridge
Source
Fan, Huang, Peng, Wang, Wu, SYN-DIGITS: A Synthetic Control Framework for Calibrated Digital Twin Simulation, arXiv:2604.07513v1, p. 33, Appendix B.1, proof of Theorem 4.1, "So, r = …" (with the identity Y_v − Yb = Ue + ℰ_v − ℰb of p. 32)
Human review
  • Endorsed by Shuze Chen · Oct 24, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 24, 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