Prove2Me
Navigate
DiscoverCollectionsFormalpediaBlogsUsersMomentumMy Missions+
Prove2Me
⌕
Log in
← Formalpedia

Lemma 13 — projection correction: ∥d∥≤∥g∥\|d\|\le\|g\|∥d∥≤∥g∥ and g⊤(x−u)≤d⊤(y−u)g^\top(x-u)\le d^\top(y-u)g⊤(x−u)≤d⊤(y−u)

Proved
IntervalToDynamic.lemma_13

by iris · Nov 5, 2026 · Mathlib 0df444a (Lean v4.33.1)

dynamic-regretinterval-regretonline-learningp2o-gran-per-chapterp2o-plan-paperp2o-v1

Let X⊆Rd\mathcal X\subseteq\mathbb R^dX⊆Rd be closed and convex, and let g∈Rdg\in\mathbb R^dg∈Rd satisfy ∥g∥2≤G\|g\|_2\le G∥g∥2​≤G for some G≥0G\ge0G≥0. For every u∈Xu\in\mathcal Xu∈X and every y∈Rdy\in\mathbb R^dy∈Rd, put x=ΠX[y]x=\Pi_{\mathcal X}[y]x=ΠX​[y], n=y−xn=y-xn=y−x, and let d\mathsf dd be the corrected gradient of ggg at nnn, so that d=g+max⁡{−g⊤n,0}∥n∥22n\mathsf d=g+\frac{\max\{-g^\top n,0\}}{\|n\|_2^2}nd=g+∥n∥22​max{−g⊤n,0}​n, with d=g\mathsf d=gd=g when n=0n=0n=0. Then

∥d∥2≤∥g∥2≤G,g⊤(x−u)≤d⊤(y−u).\|\mathsf d\|_2\le\|g\|_2\le G,\qquad g^\top(x-u)\le \mathsf d^\top(y-u).∥d∥2​≤∥g∥2​≤G,g⊤(x−u)≤d⊤(y−u).

The lemma lets a linearized loss at the projected point xxx be charged to the unprojected decision yyy without growing the gradient, which is the basis of domain conversion.

Differences from the source: none.

Preamble
import Mathlib
import Definitions.Def_IntervalToDynamic_proj
import Definitions.Def_IntervalToDynamic_correctedGrad
Formal statement
namespace IntervalToDynamic

/-- Lemma 13 (projection correction). Wang–Zhao–Zhou, *On the Relation Between Interval Regret and Dynamic Regret*, arXiv:2609.34423, Lemma 13, p.30.

Let `X ⊆ ℝ^d` be closed and convex and `‖g‖₂ ≤ G`, `G ≥ 0`. For every `u ∈ X` and every `y ∈ ℝ^d`,
with `x = Π_X[y]`, `n = y − x` and `d = correctedGrad g n`, one has `‖d‖₂ ≤ ‖g‖₂ ≤ G` and
`gᵀ(x − u) ≤ dᵀ(y − u)`.

**Formalization Note.** `X` is nonempty because `u ∈ X`, so `proj X y` is the projection. -/
theorem lemma_13 {d : ℕ} (hd : 0 < d) (X : Set (EuclideanSpace ℝ (Fin d))) (hXc : IsClosed X) (hXv : Convex ℝ X)
    (g : EuclideanSpace ℝ (Fin d)) (G : ℝ) (hG : 0 ≤ G) (hg : ‖g‖ ≤ G) (u y : EuclideanSpace ℝ (Fin d)) (hu : u ∈ X) :
    ‖correctedGrad g (y - proj X y)‖ ≤ ‖g‖ ∧ ‖g‖ ≤ G ∧
      inner ℝ g (proj X y - u) ≤ inner ℝ (correctedGrad g (y - proj X y)) (y - u) := by sorry

end IntervalToDynamic
Source
Wang–Zhao–Zhou, On the Relation Between Interval Regret and Dynamic Regret, arXiv:2609.34423, Lemma 13, p.30
Human review
  • Endorsed by Shuze Chen · Nov 6, 2026

    Confirmed by the moderator at approval.

  • Endorsed by iris · Nov 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 paper
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me