Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 3 — regret of composite mirror descent with time-varying quadratic proximal functions, (11)

Proved
AdaGrad.Full.proposition_3

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

mirror-descentonline-learningp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1regret

Let X⊆Rd\mathcal X\subseteq\mathbb R^dX⊆Rd be closed and convex, ftf_tft​ and φ\varphiφ convex, η>0\eta>0η>0, T≥1T\ge1T≥1, and let x1,…,xT+1x_1,\dots,x_{T+1}x1​,…,xT+1​ be generated by the composite mirror descent update (4) with ψt(x)=12⟨x,Htx⟩\psi_t(x)=\tfrac12\langle x,H_tx\rangleψt​(x)=21​⟨x,Ht​x⟩, where for t=1,…,Tt=1,\dots,Tt=1,…,T the matrix HtH_tHt​ is positive semidefinite and gtg_tgt​ lies in its range. Assume x1∈Xx_1\in\mathcal Xx1​∈X minimizes φ\varphiφ over X\mathcal XX. Then for every x∗∈Xx^*\in\mathcal Xx∗∈X,

∑t=1Tft(xt)+φ(xt)−ft(x∗)−φ(x∗)≤1ηBψ1(x∗,x1)+1η∑t=1T−1[Bψt+1(x∗,xt+1)−Bψt(x∗,xt+1)]+η2∑t=1T∥gt∥ψt∗2,\sum_{t=1}^T f_t(x_t)+\varphi(x_t)-f_t(x^*)-\varphi(x^*)\le\frac1\eta B_{\psi_1}(x^*,x_1)+\frac1\eta\sum_{t=1}^{T-1}\big[B_{\psi_{t+1}}(x^*,x_{t+1})-B_{\psi_t}(x^*,x_{t+1})\big]+\frac\eta2\sum_{t=1}^T\|g_t\|_{\psi_t^*}^2,t=1∑T​ft​(xt​)+φ(xt​)−ft​(x∗)−φ(x∗)≤η1​Bψ1​​(x∗,x1​)+η1​t=1∑T−1​[Bψt+1​​(x∗,xt+1​)−Bψt​​(x∗,xt+1​)]+2η​t=1∑T​∥gt​∥ψt∗​2​,

with ∥g∥ψt∗2=⟨g,Ht†g⟩\|g\|_{\psi_t^*}^2=\langle g,H_t^\dagger g\rangle∥g∥ψt∗​2​=⟨g,Ht†​g⟩.

This reduces the regret of every adaptive mirror-descent method to the growth of its proximal terms and a sum of dual norms.

Formalization Note Specialised to quadratic proximal functions, with the range condition as in Lemma 16. The paper's "assume w.l.o.g. that φ(x1)=0\varphi(x_1)=0φ(x1​)=0" (with x1=arg⁡min⁡Xφx_1=\arg\min_{\mathcal X}\varphix1​=argminX​φ, p. 2123) is stated as: x1∈Xx_1\in\mathcal Xx1​∈X minimizes φ\varphiφ over X\mathcal XX. No monotonicity of HtH_tHt​ is assumed (the proof does not use it). The number of rounds is T≥1T\ge1T≥1 (at T=0T=0T=0 nothing would constrain H1H_1H1​ in the term Bψ1B_{\psi_1}Bψ1​​).

Preamble
import Mathlib
import Definitions.Def_AdaGrad_Full_Algorithm2
open scoped MatrixOrder InnerProductSpace
Formal statement
namespace AdaGrad.Full

/-- Proposition 3, inequality (11) (p. 2129), specialised to quadratic proximal functions
`ψ_t(x) = ½⟨x, H_t x⟩` with `H_t` positive semidefinite and `g_t` in the range of `H_t`, over `T ≥ 1` rounds. -/
theorem proposition_3 {d : ℕ} (η : ℝ) (hη : 0 < η) (X : Set (EuclideanSpace ℝ (Fin d)))
    (hXc : Convex ℝ X) (hXcl : IsClosed X)
    (f : ℕ → EuclideanSpace ℝ (Fin d) → ℝ) (hf : ∀ t, ConvexOn ℝ Set.univ (f t))
    (ϕ : EuclideanSpace ℝ (Fin d) → ℝ) (hϕ : ConvexOn ℝ Set.univ ϕ)
    (H : ℕ → Matrix (Fin d) (Fin d) ℝ) (x g : ℕ → EuclideanSpace ℝ (Fin d)) (T : ℕ) (hT : 1 ≤ T)
    (hH : ∀ t ∈ Finset.Icc 1 T, (H t).PosSemidef)
    (hrange : ∀ t ∈ Finset.Icc 1 T, g t ∈ LinearMap.range (Matrix.toEuclideanLin (H t)))
    (hrun : IsQuadMirrorDescentRun η X ϕ f H x g T)
    (hx1 : x 1 ∈ X) (hϕx1 : ∀ y ∈ X, ϕ (x 1) ≤ ϕ y)
    (xstar : EuclideanSpace ℝ (Fin d)) (hstar : xstar ∈ X) :
    AdaGrad.Diag.regret f ϕ x xstar T ≤
      1 / η * bregman (H 1) xstar (x 1)
        + 1 / η * ∑ t ∈ Finset.Ico 1 T,
            (bregman (H (t + 1)) xstar (x (t + 1)) - bregman (H t) xstar (x (t + 1)))
        + η / 2 * ∑ t ∈ Finset.Icc 1 T, dualNormSq (H t) (g t) := by sorry

end AdaGrad.Full
Source
Duchi, Hazan, Singer, Adaptive Subgradient Methods for Online Learning and Stochastic Optimization, JMLR 12 (2011), p. 2129, Proposition 3, (11)
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