Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition D.2 (FTRL bound) — RegT(u)≤16dlog⁡(eK)+21dTlog⁡(eK)\mathrm{Reg}_T(u)\le 16d\log(eK)+21\sqrt{dT\log(eK)}RegT​(u)≤16dlog(eK)+21dTlog(eK)​

Proved
IAFTRL.proposition_D_2_ftrl

by Canzhe Zhao · Nov 15, 2026 · Mathlib 0df444a (Lean v4.33.1)

bandit-algorithmslinear-banditsonline-learning

Let d≥1d\ge1d≥1 and let A={a1,…,aK}\mathcal A=\{a_1,\dots,a_K\}A={a1​,…,aK​} be a finite action set in the Euclidean unit ball of Rd\mathbb R^dRd that spans Rd\mathbb R^dRd. Consider any execution of IA-FTRL for T≥1T\ge1T≥1 rounds against an adaptive environment whose loss vectors satisfy ∥θt∥A=max⁡a∈A∣a⊤θt∣≤1\|\theta_t\|_{\mathcal A}=\max_{a\in\mathcal A}|a^\top\theta_t|\le1∥θt​∥A​=maxa∈A​∣a⊤θt​∣≤1, and write RegT(u)=E[∑t=1T(At−u)⊤θt]\mathrm{Reg}_T(u)=\mathbb E\big[\sum_{t=1}^T(A_t-u)^\top\theta_t\big]RegT​(u)=E[∑t=1T​(At​−u)⊤θt​] for the regret against a comparator u∈Au\in\mathcal Au∈A. Then for every u∈Au\in\mathcal Au∈A,

RegT(u)≤16 dlog⁡(eK)+21dTlog⁡(eK).\mathrm{Reg}_T(u)\le 16\,d\log(eK)+21\sqrt{dT\log(eK)} .RegT​(u)≤16dlog(eK)+21dTlog(eK)​.

This is the substantive term of the all-history adversarial guarantee in Proposition D.2. It holds on every history, with no moment event or objective comparison, and it yields the minimax-order bound (2.4) of Proposition 2.1.

Formalization Note Same hypotheses as IAFTRL.proposition_D_2. Together with IAFTRL.proposition_D_2_trivial it gives that proposition.

Preamble
import Mathlib
import Definitions.Def_IAFTRL_IsActionSet
import Definitions.Def_IAFTRL_IsIAFTRLRun
import Definitions.Def_IAFTRL_regretVs
Formal statement
namespace IAFTRL

open Matrix MeasureTheory

/-- **Proposition D.2, FTRL bound.** Zhao–Tan, *Best-of-Both-Worlds FTRL for Linear Bandits*,
arXiv:2611.01299, Proposition D.2, p.67: "IA-FTRL satisfies, for every `T ≥ 1`,
`sup_{u∈𝒜} Reg_T(u) ≤ min{2T, 16d log(eK) + 21√(dT log(eK))}`. No moment event or objective
comparison is required for this bound." — the second term of the minimum.

For every execution of IA-FTRL for `T ≥ 1` rounds against an adaptive environment (spanning finite
action set in the unit ball of `ℝ^d`, `d ≥ 1`) and every comparator action `u`:
`Reg_T(u) ≤ 16d log(eK) + 21√(dT log(eK))`.

**Formalization Note.** Same hypotheses as `IAFTRL.proposition_D_2`; together with
`IAFTRL.proposition_D_2_trivial` it gives that proposition. -/
theorem proposition_D_2_ftrl {d K : ℕ} (hd : 1 ≤ d) (arms : Fin K → Fin d → ℝ)
    (hA : IsActionSet arms) {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω)
    [IsProbabilityMeasure P] (T : ℕ) (hT : 1 ≤ T) (R : Run d K Ω) (hR : IsIAFTRLRun P arms T R)
    (u : Fin K) :
    regretVs P arms T R u ≤
      16 * (d : ℝ) * Real.log (Real.exp 1 * K) +
        21 * Real.sqrt ((d : ℝ) * T * Real.log (Real.exp 1 * K)) := by sorry

end IAFTRL
Source
Zhao–Tan, Best-of-Both-Worlds FTRL for Linear Bandits, arXiv:2611.01299, Proposition D.2, p.67 (second term of the minimum)

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