Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proof of Thm 1.1(b), p. 303 — Σ M(s_{1:t}+p₁)·s_t ≤ M(s_{1:T})·s_{1:T} + D|p₁|_∞

Proved
KalaiVempala.Multiplicative.bound_shared_perturbation

by mikedeng1 · Oct 7, 2026 · Mathlib 0df444a (Lean v4.33.1)

be-the-leaderfollow-the-perturbed-leaderonline-learningp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1

Let D⊂Rn\mathcal D \subset \mathbb R^nD⊂Rn be a decision set whose ℓ1\ell_1ℓ1​-diameter is at most DDD, i.e. ∣d−d′∣1≤D|d - d'|_1 \le D∣d−d′∣1​≤D for all d,d′∈Dd, d' \in \mathcal Dd,d′∈D, and let MMM be an argmin oracle for D\mathcal DD. For every state sequence s1,…,sT∈Rns_1, \dots, s_T \in \mathbb R^ns1​,…,sT​∈Rn and every fixed perturbation vector p1∈Rnp_1 \in \mathbb R^np1​∈Rn,

∑t=1TM(s1:t+p1)⋅st  ≤  M(s1:T)⋅s1:T+D ∣p1∣∞.\sum_{t=1}^T M(s_{1:t} + p_1)\cdot s_t \;\le\; M(s_{1:T})\cdot s_{1:T} + D\,|p_1|_\infty .t=1∑T​M(s1:t​+p1​)⋅st​≤M(s1:T​)⋅s1:T​+D∣p1​∣∞​.

This is the "be the perturbed leader" bound with one perturbation shared by all periods, the special case pt=p1p_t = p_1pt​=p1​ of Lemma 3.1 of the paper. It is the deterministic half of the proof of Theorem 1.1(b): the perturbation costs at most DDD times its sup norm.

Formalization Note ∣p1∣∞|p_1|_\infty∣p1​∣∞​ is the Lean norm ‖p₁‖, which on Fin n → ℝ is the sup norm. The bound holds for arbitrary real states; the set S\mathcal SS, the nonnegativity of D\mathcal DD and S\mathcal SS, and the parameters RRR, AAA are not used and are not hypotheses.

Preamble
import Mathlib
import Definitions.Def_OracleRO_ApproxFPL_FPL
import Definitions.Def_KalaiVempala_Multiplicative_Setting

open MeasureTheory OracleRO.ApproxFPL
Formal statement
namespace KalaiVempala.Multiplicative

theorem bound_shared_perturbation {n : ℕ} (Dset : Set (Fin n → ℝ))
    (M : (Fin n → ℝ) → (Fin n → ℝ)) (hM : KalaiVempala.Additive.IsArgminOracle Dset M)
    (Ddiam : ℝ) (hD : ∀ d ∈ Dset, ∀ d' ∈ Dset, ∑ i, |d i - d' i| ≤ Ddiam)
    (s : ℕ → Fin n → ℝ) (T : ℕ) (p₁ : Fin n → ℝ) :
    ∑ t ∈ Finset.Icc 1 T, M (prefixSum s t + p₁) ⬝ᵥ s t ≤
      M (prefixSum s T) ⬝ᵥ prefixSum s T + Ddiam * ‖p₁‖ := by sorry

end KalaiVempala.Multiplicative
Source
Kalai & Vempala, Efficient algorithms for online decision problems, J. Comput. System Sci. 71 (2005), p. 303, proof of Theorem 1.1(b), first display (by Lemma 3.1, p. 300)
Human review
  • Endorsed by Shuze Chen · Oct 7, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 7, 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