Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§3, after (13) — with δ ≥ maxₜ‖gₜ‖∞, Σₜ‖gₜ‖²_{ψ*_{t−1}} ≤ 2 Σᵢ‖g_{1:T,i}‖₂

Proved
AdaGrad.Diag.primal_dual_gradient_term

by mikedeng1 · Oct 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

adaptive-methodsonline-learningp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1

Let g1,g2,⋯∈Rdg_1,g_2,\dots\in\mathbb R^dg1​,g2​,⋯∈Rd be any sequence, st,i=∥g1:t,i∥2s_{t,i}=\|g_{1:t,i}\|_2st,i​=∥g1:t,i​∥2​ (with s0,i=0s_{0,i}=0s0,i​=0), TTT a horizon and δ≥0\delta\ge0δ≥0 with δ≥max⁡1≤t≤T∥gt∥∞\delta\ge\max_{1\le t\le T}\|g_t\|_\inftyδ≥max1≤t≤T​∥gt​∥∞​. With AdaGrad's proximal functions ψt(x)=12⟨x,(δI+diag(st))x⟩\psi_t(x)=\frac12\langle x,(\delta I+\mathrm{diag}(s_t))x\rangleψt​(x)=21​⟨x,(δI+diag(st​))x⟩, whose squared dual norms are ∥g∥ψt∗2=∑igi2/(δ+st,i)\|g\|^2_{\psi_t^*}=\sum_ig_i^2/(\delta+s_{t,i})∥g∥ψt∗​2​=∑i​gi2​/(δ+st,i​),

∑t=1T∥gt∥ψt−1∗2≤2∑i=1d∥g1:T,i∥2.\sum_{t=1}^T\|g_t\|^2_{\psi_{t-1}^*}\le2\sum_{i=1}^d\|g_{1:T,i}\|_2 .t=1∑T​∥gt​∥ψt−1∗​2​≤2i=1∑d​∥g1:T,i​∥2​.

This is the inequality (13) for the primal-dual subgradient update, whose regret bound (Proposition 2) measures round ttt's subgradient in the dual norm of the previous round's proximal function.

Formalization Note The page states the per-round comparison with ⟨gt,diag(st)−1gt⟩\langle g_t,\mathrm{diag}(s_t)^{-1}g_t\rangle⟨gt​,diag(st​)−1gt​⟩ and says the same reasoning gives (13); the statement here is that summed conclusion. Division uses Lean's 0/0=00/0=00/0=0.

Preamble
import Mathlib
import Definitions.Def_AdaGrad_Diag_Setup
Formal statement
namespace AdaGrad.Diag

/-- Duchi, Hazan, Singer, JMLR 12 (2011), §3, paragraph after (13), p. 2131: if
`δ ≥ max_{t ≤ T} ‖g_t‖∞`, then the squared dual norms for the *previous* round's proximal
function `ψ_{t−1}(x) = ½⟨x, (δI + diag(s_{t−1})) x⟩` (with `s_0 = 0`) satisfy the inequality (13):
`∑_{t=1}^T ‖g_t‖²_{ψ_{t−1}*} = ∑_{t=1}^T ∑_i g_{t,i}² / (δ + s_{t−1,i}) ≤ 2 ∑_{i=1}^d ‖g_{1:T,i}‖₂`. -/
theorem primal_dual_gradient_term {d : ℕ} (g : ℕ → EuclideanSpace ℝ (Fin d)) (δ : ℝ)
    (hδ : 0 ≤ δ) (T : ℕ) (hδg : ∀ t ∈ Finset.Icc 1 T, supNorm (g t) ≤ δ) :
    ∑ t ∈ Finset.Icc 1 T, dualNormSq (adaWeights δ g (t - 1)) (g t) ≤ 2 * ∑ i, s g T i := by sorry

end AdaGrad.Diag
Source
Duchi, Hazan, Singer, Adaptive Subgradient Methods for Online Learning and Stochastic Optimization, JMLR 12 (2011), p. 2131, §3, paragraph after (13)
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