Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Eq. (13) — without projection, w_{t+1} = (1/(λt)) Σ_{i≤t} v_i

Proved
Pegasos.Analysis.eq_13

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

p2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1stochastic-subgradientsvm

Let λ>0\lambda>0λ>0 and run mini-batch Pegasos (Fig. 2) without the projection step, on any sequence of mini-batches A1,A2,…A_1, A_2,\dotsA1​,A2​,… of kkk indices. Write

vi=1k∑j∈Ai1[yj⟨wi,xj⟩<1] yjxj.v_i = \frac{1}{k}\sum_{j\in A_i}\mathbb 1\bigl[y_j\langle w_i, x_j\rangle < 1\bigr]\, y_j x_j .vi​=k1​j∈Ai​∑​1[yj​⟨wi​,xj​⟩<1]yj​xj​.

Then for every t≥1t\ge1t≥1

wt+1=1λt∑i=1tvi.w_{t+1} = \frac{1}{\lambda t}\sum_{i=1}^t v_i .wt+1​=λt1​i=1∑t​vi​.

Writing the unprojected iterate as an average of margin-violation vectors is what yields the norm bound ∥wt+1∥≤R/λ\|w_{t+1}\|\le R/\lambda∥wt+1​∥≤R/λ.

Formalization Note. The paper's intermediate display (12) is printed as wt+1=(1−1t)wt−1tλvtw_{t+1} = (1-\frac1t)w_t - \frac{1}{t\lambda}v_twt+1​=(1−t1​)wt​−tλ1​vt​ with xtx_txt​ inside the indicator; since ∇t=λwt−vt\nabla_t = \lambda w_t - v_t∇t​=λwt​−vt​ the correct update is wt+1=(1−1t)wt+1tλvtw_{t+1} = (1-\frac1t)w_t + \frac{1}{t\lambda}v_twt+1​=(1−t1​)wt​+tλ1​vt​ with xjx_jxj​ in the indicator. Eq. (13) is correct as printed and is what is stated. Iterations are 1-based with w1=0w_1 = 0w1​=0.

Preamble
import Mathlib
import Definitions.Def_Pegasos_Analysis_Model
Formal statement
namespace Pegasos.Analysis

/-- **Eq. (13)** (p. 11): without the projection step, for every `t ≥ 1`,
`w_{t+1} = (1/(λt)) Σ_{i=1}^t v_i` with `v_i = (1/k) Σ_{j∈A_i} 1l[y_j⟨w_i, x_j⟩ < 1] y_j x_j`. -/
theorem eq_13 {n m k : ℕ} (lam : ℝ) (hlam : 0 < lam)
    (x : Fin m → EuclideanSpace ℝ (Fin n)) (y : Fin m → ℝ) (A : ℕ → Fin k → Fin m)
    (t : ℕ) (ht : 1 ≤ t) :
    run lam x y A false (t + 1)
      = (1 / (lam * (t : ℝ))) • ∑ i ∈ Finset.Icc 1 t, hingeTerm x y (A i) (run lam x y A false i) := by sorry

end Pegasos.Analysis
Source
Shalev-Shwartz, Singer, Srebro & Cotter, Pegasos: primal estimated sub-gradient solver for SVM, Math. Program. 127 (2011), p. 11, Eq. (13) (proof of Theorem 1)
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 7, 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