Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition G.1 — corrupted sharp-instance bound of GIA-FTRL for each allocation

Proved
IAFTRL.proposition_G_1

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

bandit-algorithmslinear-banditsonline-learning

Setting. The setting is that of Proposition 3.1.

  • A⊆Bd\mathcal A\subseteq\mathbb B^dA⊆Bd is compact and spanning, B\mathcal BB is a compact generator with k≥1k\ge1k≥1, and eee is a surjective enumeration of Qd\mathbb Q^dQd.
  • The instance (θ,a∗)(\theta,a^*)(θ,a∗) satisfies ∥θ∥A≤1\|\theta\|_{\mathcal A}\le1∥θ∥A​≤1; a∗∈Aa^*\in\mathcal Aa∗∈A is the unique minimizer of a↦a⊤θa\mapsto a^\top\thetaa↦a⊤θ on A\mathcal AA; and the instance is sharp: ς∥a−a∗∥S≤(a−a∗)⊤θ\varsigma\|a-a^*\|_{\mathcal S}\le(a-a^*)^\top\thetaς∥a−a∗∥S​≤(a−a∗)⊤θ on Conv A\mathrm{Conv}\,\mathcal AConvA for some ς>0\varsigma>0ς>0.

Claim. There is JJJ such that for every finite feasible centered sampling allocation nnn on B\mathcal BB there is MMM, independent of TTT, CCC and the run, with the following property. For every GIA-FTRL run of T≥1T\ge1T≥1 rounds in the corrupted stochastic regime with budget C≥0C\ge0C≥0 (that is, ∑t<T∥θt−θ∥A≤C\sum_{t<T}\|\theta_t-\theta\|_{\mathcal A}\le C∑t<T​∥θt​−θ∥A​≤C almost surely), and every u∈Au\in\mathcal Au∈A,

RegT(u)≤16 B Crat4 cctrn(B,θ)log⁡(eT)+M+JC log⁡(e+C),\mathrm{Reg}_T(u)\le 16\,B\,C_{\mathrm{rat}}^4\,c^n_{\mathrm{ctr}}(\mathcal B,\theta)\log(eT)+M+J\sqrt C\,\log(e+C),RegT​(u)≤16BCrat4​cctrn​(B,θ)log(eT)+M+JC​log(e+C),

where B=236(d+1)B=2^{36}(d+1)B=236(d+1) and Crat=64C_{\mathrm{rat}}=64Crat​=64.

Proof outline (Appendix G.1.1). The regret against a∗a^*a∗ splits into a penalty term, a stability term, an exploration term and a direct corruption term (G.3)–(G.5). These are bounded by Lemmas G.1, G.4, G.5 and G.9 on the good events, together with the weighted failure estimate. The comparator correction for u≠a∗u\ne a^*u=a∗ is then handled explicitly.

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

open MeasureTheory

/-- **Proposition G.1 (Corrupted sharp-instance bound for each sampling allocation).** Zhao–Tan,
*Best-of-Both-Worlds FTRL for Linear Bandits* (STOC submission version), Proposition G.1,
pp.123–124: "GIA-FTRL, with a fixed finite feasible centered sampling allocation `n_des`,
satisfies for every `T ≥ 1` and every allowed budget `C ≥ 0` …
`Reg_T ≤ 16 B C_rat⁴ c^{n_des}_ctr log(eT) + M_{n_des} + J^cor_θ √C log(e + C)` (G.2)", with
`B = 2^36(d+1)` and `C_rat = 64` (G.264); `J^cor_θ` does not depend on the allocation.

The setting is that of `proposition_3_1` (sharp instance `(θ, a*)`, `‖θ‖_𝒜 ≤ 1`, unique
optimal action `a* ∈ 𝒜`); `n` is a finite feasible centered sampling allocation on the generator
`ℬ`, `J` is chosen before `n`, and `M` depends on `n` but not on `T, C` or the run. -/
theorem proposition_G_1 {d : ℕ} (hd : 1 ≤ d) (𝒜 ℬ : Set (Fin d → ℝ)) (e : ℕ → Fin d → ℚ)
    (h𝒜 : IsCompact 𝒜) (hℬ : IsCompact ℬ) (hgen : IsGenerator 𝒜 ℬ)
    (hball : ∀ a ∈ 𝒜, a ⬝ᵥ a ≤ 1) (hspan : Submodule.span ℝ 𝒜 = ⊤) (hk : 1 ≤ kdim ℬ)
    (he : Function.Surjective e) (θ astar : Fin d → ℝ) (hθ : setNorm 𝒜 θ ≤ 1)
    (hastar : astar ∈ 𝒜) (huniq : ∀ a ∈ 𝒜, a ≠ astar → astar ⬝ᵥ θ < a ⬝ᵥ θ)
    (hsharp : IsSharp 𝒜 θ astar) :
    ∃ J : ℝ, ∀ n : Measure (Fin d → ℝ), IsCtrAlloc ℬ θ astar n →
      ∃ M : ℝ, ∀ {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) [IsProbabilityMeasure P]
        (T : ℕ) (C : ℝ) (R : GRun d Ω), 1 ≤ T → 0 ≤ C →
        IsGIAFTRLRun P 𝒜 ℬ e T R → IsCorruptedG P 𝒜 θ C T R →
        ∀ u ∈ 𝒜, gRegretVs P T R u ≤
          16 * gB d * 64 ^ 4 * ctrCost θ astar n * Real.log (Real.exp 1 * T) + M +
            J * Real.sqrt C * Real.log (Real.exp 1 + C) := 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 G.1.1, Proposition G.1, pp. 123–124

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