Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Theorem 2.13, p. 13 — constant-step gradient bound for linear losses on all of Euclidean space

Proved
ModernOnlineLearning.Classification.theorem_2_13

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

gradient-descentonline-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-bookp2o-v1regret

Consider linear losses with gradient vectors gt∈Rdg_t\in\mathbb R^dgt​∈Rd. Let η>0\eta>0η>0 be fixed and let xt+1=xt−ηgtx_{t+1}=x_t-\eta g_txt+1​=xt​−ηgt​ for rounds t=1,…,Tt=1,\ldots,Tt=1,…,T. For every u∈Rdu\in\mathbb R^du∈Rd,

∑t=1T⟨gt,xt−u⟩≤∥u−x1∥222η+η2∑t=1T∥gt∥22−∥xT+1−u∥222η.\sum_{t=1}^T\langle g_t,x_t-u\rangle \le \frac{\|u-x_1\|_2^2}{2\eta} +\frac\eta2\sum_{t=1}^T\|g_t\|_2^2 -\frac{\|x_{T+1}-u\|_2^2}{2\eta}.t=1∑T​⟨gt​,xt​−u⟩≤2η∥u−x1​∥22​​+2η​t=1∑T​∥gt​∥22​−2η∥xT+1​−u∥22​​.

This is the constant-step part of Theorem 2.13 specialized to the unprojected linear losses used in the Perceptron analysis.

Formalization Note The book states the theorem for a closed convex feasible set and convex differentiable losses. The Lean statement uses the stated linear-loss, whole-space specialization, so the linear loss difference is exactly ⟨gt,xt−u⟩\langle g_t,x_t-u\rangle⟨gt​,xt​−u⟩. No bounded diameter is needed in this part.

Preamble
import Mathlib
import Definitions.Def_ModernOnlineLearning_Classification_Perceptron
Formal statement
namespace ModernOnlineLearning.Classification

/-- Orabona, Theorem 2.13, constant-step linear-loss case on all of `ℝ^d`, p. 13.
The update is unprojected gradient descent. -/
theorem theorem_2_13 {d : ℕ} (T : ℕ) (η : ℝ) (hη : 0 < η)
    (g x : ℕ → ModernOnlineLearning.Adaptive.Vec d)
    (hrun : ∀ t ∈ Finset.Icc 1 T, x (t + 1) = x t - η • g t)
    (u : ModernOnlineLearning.Adaptive.Vec d) :
    (∑ t ∈ Finset.Icc 1 T, inner ℝ (g t) (x t - u)) ≤
      ‖u - x 1‖ ^ 2 / (2 * η) +
        η / 2 * (∑ t ∈ Finset.Icc 1 T, ‖g t‖ ^ 2) -
        ‖x (T + 1) - u‖ ^ 2 / (2 * η) := by sorry

end ModernOnlineLearning.Classification
Source
Orabona, arXiv:1912.13213v10, Theorem 2.13, constant-step clause, p. 13; specialization used in proof of Theorem 8.2, p. 145
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 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