Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Appendix F.1.1 — a fixed comparison allocation with cctrn≤2cctr∗c^{n}_{\mathrm{ctr}}\le 2c^*_{\mathrm{ctr}}cctrn​≤2cctr∗​

Proved
IAFTRL.theorem_3_1_alloc

by Canzhe Zhao · Nov 17, 2026 · Mathlib 0df444a (Lean v4.33.1)

bandit-algorithmslinear-banditsonline-learning

Let A⊆Bd\mathcal A\subseteq\mathbb B^dA⊆Bd (d≥1d\ge1d≥1) be a compact action set with span(A)=Rd\mathrm{span}(\mathcal A)=\mathbb R^dspan(A)=Rd, and let B\mathcal BB be a compact generator, so B⊆A⊆Conv(B)\mathcal B\subseteq\mathcal A\subseteq\mathrm{Conv}(\mathcal B)B⊆A⊆Conv(B). Let θ\thetaθ have a unique optimal action a∗∈Aa^*\in\mathcal Aa∗∈A, and suppose the instance is sharp (1.3).

Then there is a finite feasible centered sampling allocation n∘n^\circn∘ on B\mathcal BB with

cctrn∘(B,θ)≤2 cctr∗(B,θ).c^{n^\circ}_{\mathrm{ctr}}(\mathcal B,\theta)\le2\,c^*_{\mathrm{ctr}}(\mathcal B,\theta).cctrn∘​(B,θ)≤2cctr∗​(B,θ).

This is the choice of the fixed comparison allocation in Appendix F.1.1.

  • When cctr∗>0c^*_{\mathrm{ctr}}>0cctr∗​>0, the allocation comes from the definition of the infimum, (F.2).
  • When cctr∗=0c^*_{\mathrm{ctr}}=0cctr∗​=0, the source constructs an exact zero-cost allocation, (F.3)–(F.8).

Together with Proposition 3.1 and Lemma J.10, it yields Theorem 3.1.

Preamble
import Mathlib
import Definitions.Def_IAFTRL_LinEnv
import Definitions.Def_IAFTRL_GIAFTRL
Formal statement
namespace IAFTRL

open MeasureTheory

/-- **A fixed finite comparison sampling allocation (Appendix F.1.1).** Zhao–Tan,
*Best-of-Both-Worlds FTRL for Linear Bandits* (STOC submission version), Appendix F.1.1,
(F.1)–(F.8), pp.120–121: "`c*_ctr > 0 ⟹ ∃ n° ∈ N_θ : c^{n°}_ctr ≤ 2c*_ctr` (F.2) … Use `n° = n₀`
when `c*_ctr = 0`. In both cases, `c^{n°}_ctr ≤ 2c*_ctr`", applied on the physical generator `ℬ`.

For a compact generator `ℬ` of a compact action set `𝒜 ⊆ 𝔹^d` spanning `ℝ^d`, a unique optimal
action `a* ∈ 𝒜` under `θ`, and sharpness (1.3), there is a finite feasible centered sampling
allocation `n°` on `ℬ` with `c^{n°}_ctr(ℬ, θ) ≤ 2 c*_ctr(ℬ, θ)`. -/
theorem theorem_3_1_alloc {d : ℕ} (hd : 1 ≤ d) (𝒜 ℬ : Set (Fin d → ℝ)) (h𝒜 : IsCompact 𝒜)
    (hℬ : IsCompact ℬ) (hgen : IsGenerator 𝒜 ℬ) (hball : ∀ a ∈ 𝒜, a ⬝ᵥ a ≤ 1)
    (hspan : Submodule.span ℝ 𝒜 = ⊤) (θ astar : Fin d → ℝ) (hastar : astar ∈ 𝒜)
    (huniq : ∀ a ∈ 𝒜, a ≠ astar → astar ⬝ᵥ θ < a ⬝ᵥ θ) (hsharp : IsSharp 𝒜 θ astar) :
    ∃ n : Measure (Fin d → ℝ), IsCtrAlloc ℬ θ astar n ∧
      ctrCost θ astar n ≤ 2 * cstarCtr ℬ θ astar := by sorry

end IAFTRL
Source
Zhao–Tan, Best-of-Both-Worlds FTRL for Linear Bandits: The Interplay of Information Acquisition, Corruption, and Geometry (STOC submission version; arXiv:2611.01299), Appendix F.1.1, (F.1)–(F.8), pp. 120–121

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