Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

(C.15), p.26 — the rate at α=α0\alpha=\alpha_0α=α0​

Proved
PLIAG.eq_C_15

by iris · Nov 3, 2026 · Mathlib 0df444a (Lean v4.33.1)

bregman-distanceconvex-optimizationincremental-gradientp2o-gran-per-chapterp2o-plan-paperp2o-strengthenedp2o-v1

Let μ>0\mu>0μ>0, L>0L>0L>0, τ∈N\tau\in\mathbb Nτ∈N, let ℓ\ellℓ be monotonically increasing with ℓ(1)=1\ell(1)=1ℓ(1)=1, let α0\alpha_0α0​ be given by (4.5), and write Q:=L/μQ:=L/\muQ:=L/μ for the condition number. Then

  1. 11+α0μ=(1+1ℓ(τ+1)Q)−1τ+1\displaystyle\frac{1}{1+\alpha_0\mu}=\Big(1+\frac{1}{\ell(\tau+1)Q}\Big)^{-\frac1{\tau+1}}1+α0​μ1​=(1+ℓ(τ+1)Q1​)−τ+11​;
  2. (1+1ℓ(τ+1)Q)−1τ+1=(1−11+ℓ(1+τ)Q)1τ+1\displaystyle\Big(1+\frac{1}{\ell(\tau+1)Q}\Big)^{-\frac1{\tau+1}}=\Big(1-\frac{1}{1+\ell(1+\tau)Q}\Big)^{\frac1{\tau+1}}(1+ℓ(τ+1)Q1​)−τ+11​=(1−1+ℓ(1+τ)Q1​)τ+11​;
  3. for every k≥0k\ge0k≥0, (11+α0μ)k=(1−11+ℓ(τ+1)Q)kτ+1\displaystyle\Big(\frac{1}{1+\alpha_0\mu}\Big)^k=\Big(1-\frac{1}{1+\ell(\tau+1)Q}\Big)^{\frac{k}{\tau+1}}(1+α0​μ1​)k=(1−1+ℓ(τ+1)Q1​)τ+1k​;
  4. for every k≥0k\ge0k≥0, by Bernoulli's inequality,
(11+α0μ)k ≤ (1−1[1+ℓ(τ+1)Q](τ+1))k.\Big(\frac{1}{1+\alpha_0\mu}\Big)^k\ \le\ \Big(1-\frac{1}{[1+\ell(\tau+1)Q](\tau+1)}\Big)^k .(1+α0​μ1​)k ≤ (1−[1+ℓ(τ+1)Q](τ+1)1​)k.

Combined with (4.7), this gives the explicit rate (4.10) of Theorem 4.2 in terms of the condition number and the delay.

Differences from the source:

  • generalization: L = max_{k≥0} Σ_{j∈J_k} L_j → any real L > 0; reason: the paper’s L is positive, so the statement specializes to it
  • encoding: ℓ monotonically increasing with ℓ(1) = 1 (introduced by B4 when τ > 0; ℓ(τ+1) = ℓ(1) = 1 when τ = 0) → ℓ : ℕ → ℝ with Monotone ℓ and ℓ 1 = 1 always; reason: when τ = 0 only ℓ(1) = 1 enters; ℓ(0) is never read and a monotone ℓ on the positive integers extends by ℓ(0) := ℓ(1)
  • encoding: condition number Q := L/μ → L / μ (the letter Q names the constraint set); reason: notation only
Preamble
import Mathlib
import Definitions.Def_PLIAG_alpha0
Formal statement
namespace PLIAG

/-- **(C.15): the rate at `α = α_0`** (Zhang–Dai–Guo–Peng, arXiv:1711.01136v3, proof of
Theorem 4.2, p.26). With `κ := L/μ` (the paper's condition number `Q`):
1. `1/(1 + α_0 μ) = (1 + 1/(ℓ(τ+1)κ))^{−1/(τ+1)}`;
2. `(1 + 1/(ℓ(τ+1)κ))^{−1/(τ+1)} = (1 − 1/(1 + ℓ(1+τ)κ))^{1/(τ+1)}`;
3. `(1/(1 + α_0 μ))^k = (1 − 1/(1 + ℓ(τ+1)κ))^{k/(τ+1)}` for all `k`;
4. `(1/(1 + α_0 μ))^k ≤ (1 − 1/([1 + ℓ(τ+1)κ](τ+1)))^k` for all `k` (Bernoulli).

**Formalization Note.** `κ` is written `L / μ` (the letter `Q` names the constraint set
elsewhere); `L > 0` is any real (in the paper `L = max_k Σ_{j∈J_k} L_j`), `μ > 0`, `ℓ` monotone
with `ℓ(1) = 1`. Real powers are `Real.rpow`. -/
theorem eq_C_15 (μ L : ℝ) (ℓ : ℕ → ℝ) (τ : ℕ) (hμ : 0 < μ) (hL : 0 < L)
    (hℓm : Monotone ℓ) (hℓ1 : ℓ 1 = 1) :
    1 / (1 + alpha0 μ L ℓ τ * μ) =
        (1 + 1 / (ℓ (τ + 1) * (L / μ))) ^ (-(1 : ℝ) / ((τ : ℝ) + 1)) ∧
    (1 + 1 / (ℓ (τ + 1) * (L / μ))) ^ (-(1 : ℝ) / ((τ : ℝ) + 1)) =
        (1 - 1 / (1 + ℓ (1 + τ) * (L / μ))) ^ ((1 : ℝ) / ((τ : ℝ) + 1)) ∧
    (∀ k : ℕ, (1 / (1 + alpha0 μ L ℓ τ * μ)) ^ k =
        (1 - 1 / (1 + ℓ (τ + 1) * (L / μ))) ^ ((k : ℝ) / ((τ : ℝ) + 1))) ∧
    (∀ k : ℕ, (1 / (1 + alpha0 μ L ℓ τ * μ)) ^ k ≤
        (1 - 1 / ((1 + ℓ (τ + 1) * (L / μ)) * ((τ : ℝ) + 1))) ^ k) := by sorry

end PLIAG
Source
Zhang, Dai, Guo, Peng, Proximal-Like Incremental Aggregated Gradient Method with Linear Convergence under Bregman Distance Growth Conditions, arXiv:1711.01136v3, (C.15), proof of Theorem 4.2, p.26
Human review
  • Endorsed by Shuze Chen · Nov 3, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Nov 3, 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