Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§8.3.1, p. 69 — feature-split lasso: z̄^{k+1} = (b + ρAx̄^{k+1} + ρu^k)/(N + ρ)

Proved
BoydADMM.ModelFit.feature_split_lasso_zbar_update

by mikedeng1 · Oct 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

admmfeature-splittinglassop2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-bookp2o-v1

Let N≥1N\ge1N≥1, ρ>0\rho>0ρ>0, and b,Ax‾,u∈Rmb,\overline{Ax},u\in\mathbb R^mb,Ax,u∈Rm, where Ax‾=Ax‾k+1\overline{Ax}=\overline{Ax}^{k+1}Ax=Axk+1 is the average of the partial predictors and u=uku=u^ku=uk the single scaled dual variable. For the lasso loss l(w)=12∥w∥22l(w)=\frac12\|w\|_2^2l(w)=21​∥w∥22​ the zˉ\bar zzˉ-update of feature-split ADMM minimizes

12∥Nzˉ−b∥22+Nρ2∥zˉ−Ax‾−u∥22.\frac12\|N\bar z-b\|_2^2+\frac{N\rho}{2}\|\bar z-\overline{Ax}-u\|_2^2 .21​∥Nzˉ−b∥22​+2Nρ​∥zˉ−Ax−u∥22​.

A point zˉ∈Rm\bar z\in\mathbb R^mzˉ∈Rm minimizes this function if and only if

zˉ=1N+ρ(b+ρ Ax‾+ρ u).\bar z=\frac{1}{N+\rho}\bigl(b+\rho\,\overline{Ax}+\rho\,u\bigr).zˉ=N+ρ1​(b+ρAx+ρu).

This is the closed form that makes the gathering step of the feature-split lasso a single vector operation.

Formalization Note The objective is the zˉ\bar zzˉ-update displayed on p. 68 with the lasso loss l(w)=12∥w∥22l(w)=\frac12\|w\|_2^2l(w)=21​∥w∥22​ of §8.1.1 (p. 62). The statement is an equivalence, so it includes existence and uniqueness. Ax‾\overline{Ax}Ax is taken as a given vector; how it is formed from the blocks does not matter for this identity.

Preamble
import Mathlib
import Definitions.Def_BoydADMM_ModelFit_Basic

open Matrix
Formal statement
namespace BoydADMM.ModelFit

/-- §8.3.1, p. 69: for the lasso loss `l(w) = (1/2)‖w‖₂²`, the feature-split `z̄`-update of p. 68
has the unique solution `z̄ = (b + ρ Ax̄ + ρ u)/(N + ρ)`. -/
theorem feature_split_lasso_zbar_update {N m : ℕ} (hN : 0 < N) (ρ : ℝ) (hρ : 0 < ρ)
    (b Axbar u zb : EuclideanSpace ℝ (Fin m)) :
    IsMinOn (fun z : EuclideanSpace ℝ (Fin m) =>
        1 / 2 * ‖(N : ℝ) • z - b‖ ^ 2 + (N : ℝ) * ρ / 2 * ‖z - Axbar - u‖ ^ 2) Set.univ zb ↔
      zb = (1 / ((N : ℝ) + ρ)) • (b + ρ • Axbar + ρ • u) := by sorry

end BoydADMM.ModelFit
Source
Boyd, Parikh, Chu, Peleato, Eckstein, Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers, Found. Trends Mach. Learn. 3(1) (2011), p. 69, §8.3.1 (with the z̄-update of p. 68)
Human review
  • Endorsed by Shuze Chen · Oct 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 6, 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