Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Proposition 2.1 — regret of IA-FTRL for every fixed feasible allocation

Proved
IAFTRL.proposition_2_1

by iris · Nov 6, 2026 · Mathlib 0df444a (Lean v4.33.1)

bandit-algorithmslinear-banditsonline-learningp2o-gran-per-chapterp2o-plan-bookp2o-strengthenedp2o-v1

There is an absolute constant c0>0c_0>0c0​>0 such that the following holds for every dimension d≥1d\ge1d≥1 and every finite action set A\mathcal AA in the unit ball of Rd\mathbb R^dRd spanning Rd\mathbb R^dRd, with K=∣A∣K=|\mathcal A|K=∣A∣.

  1. Adversarial regime (2.4). For every execution of IA-FTRL for T≥1T\ge1T≥1 rounds against an adaptive environment and every comparator u∈Au\in\mathcal Au∈A,
RegT(u)≤c0(dlog⁡K+dTlog⁡K).\mathrm{Reg}_T(u)\le c_0\big(d\log K+\sqrt{dT\log K}\big).RegT​(u)≤c0​(dlogK+dTlogK​).
  1. Corrupted stochastic regime (2.5). For every loss vector θ\thetaθ with ∥θ∥A≤1\|\theta\|_{\mathcal A}\le1∥θ∥A​≤1 and a unique optimal action a∗a^*a∗, every Δ0∈(0,1]\Delta_0\in(0,1]Δ0​∈(0,1] with Δ0≤Δ(a)\Delta_0\le\Delta(a)Δ0​≤Δ(a) for all a≠a∗a\ne a^*a=a∗, and every feasible sampling allocation nnn of (1.2), there is a constant MMM (depending on the instance and on nnn only) such that for every execution of IA-FTRL for T≥1T\ge1T≥1 rounds in the corrupted stochastic regime with any budget C≥0C\ge0C≥0 and every u∈Au\in\mathcal Au∈A,
RegT(u)≤c0(cn(A,θ)log⁡K⋅log⁡T+dlog⁡K Δ0−128/255C)+M.\mathrm{Reg}_T(u)\le c_0\Big(c^n(\mathcal A,\theta)\log K\cdot\log T+\sqrt{d\log K}\,\Delta_0^{-128/255}\sqrt C\Big)+M .RegT​(u)≤c0​(cn(A,θ)logK⋅logT+dlogK​Δ0−128/255​C​)+M.

Both guarantees hold for the same algorithm, which knows neither the regime nor θ\thetaθ, CCC, TTT or Δmin⁡\Delta_{\min}Δmin​.

Formalization Note O(⋅)O(\cdot)O(⋅) is read with one absolute constant. The paper's Jd,K,Δmin⁡=O(dlog⁡KΔmin⁡−128/255)J_{d,K,\Delta_{\min}}=O(\sqrt{d\log K}\Delta_{\min}^{-128/255})Jd,K,Δmin​​=O(dlogK​Δmin−128/255​) is absorbed into the c0c_0c0​-term, and c0Mnc_0M_nc0​Mn​ into MMM, which is chosen before the probability space, the horizon, the budget and the run.

Differences from the source:

  • reading: O(⋅)O(\cdot)O(⋅) → one absolute constant c0>0c_0>0c0​>0 chosen before the dimension, the action set and the instance; reason: the stronger of the two readings; an instance-dependent constant in front of the leading term would empty the statement, and the proof's constants are absolute ((C.3)–(C.5), (D.7), Proposition D.2)
  • reading: the constant MMM and Jd,K,Δmin⁡J_{d,K,\Delta_{\min}}Jd,K,Δmin​​, "independent of TTT, CCC" → ∃M\exists M∃M after (d,K,A,θ,a∗,Δ0)(d,K,\mathcal A,\theta,a^*,\Delta_0)(d,K,A,θ,a∗,Δ0​) and before the probability space, TTT, CCC and the run; JJJ absorbed into c0dlog⁡K Δ0−128/255c_0\sqrt{d\log K}\,\Delta_0^{-128/255}c0​dlogK​Δ0−128/255​; reason: MMM is defined in (D.5) from instance constants only; J=O(dlog⁡KΔmin⁡−128/255)J=O(\sqrt{d\log K}\Delta_{\min}^{-128/255})J=O(dlogK​Δmin−128/255​)
  • reading: protocol E[Yt∣Ft−1,θt,At]=At⊤θt\mathbb E[Y_t\mid\mathcal F_{t-1},\theta_t,A_t]=A_t^\top\theta_tE[Yt​∣Ft−1​,θt​,At​]=At⊤​θt​, At∼ptA_t\sim p_tAt​∼pt​ → action law given Gt\mathcal G_tGt​, feedback identity given Gt∨σ(At)\mathcal G_t\vee\sigma(A_t)Gt​∨σ(At​), for the pre-action filtration Gt\mathcal G_tGt​; reason: Appendix J.1, p.204: "Enlarging the pre-action filtration to include an environment's fresh pre-action randomization does not reveal it to the learner"
  • reading: corrupted regime: fixed θ\thetaθ → fixed θ\thetaθ with ∥θ∥A≤1\|\theta\|_{\mathcal A}\le1∥θ∥A​≤1; reason: the stochastic regime's assumption (p.5), used in the corrupted regime as 0≤κt≤20\le\kappa_t\le20≤κt​≤2 (p.86)
  • reading: IA-FTRL with "a fixed Ft−1\mathcal F_{t-1}Ft−1​-measurable rule" for ptp_tpt​ → every Ft−1\mathcal F_{t-1}Ft−1​-measurable minimizer of (2.3); reason: p.17 leaves the rule open ("e.g., the lexicographically smallest"); the proof uses only the objective comparison (C.1)/(D.158)
  • generalization: Δmin⁡∈(0,1]\Delta_{\min}\in(0,1]Δmin​∈(0,1] → any Δ0∈(0,1]\Delta_0\in(0,1]Δ0​∈(0,1] with Δ0≤Δ(a)\Delta_0\le\Delta(a)Δ0​≤Δ(a) for all a≠a∗a\ne a^*a=a∗; reason: at Δ0=Δmin⁡\Delta_0=\Delta_{\min}Δ0​=Δmin​ (assumed ≤1\le1≤1 by the paper) this is the source's bound; also covers K=1K=1K=1, where Δmin⁡\Delta_{\min}Δmin​ is undefined and the regret is 000
  • encoding: (2.1), (2.3d)–(2.3f) → softmax closed form of (2.1); computable forms of (2.3d)–(2.3f); reason: the paper states both equivalences itself (pp.18–19, (D.151))
  • encoding: sup⁡u∈ARegT\sup_{u\in\mathcal A}\mathrm{Reg}_Tsupu∈A​RegT​, rounds 1,…,T1,\dots,T1,…,T, actions as a set → a bound for every comparator action uuu; 0-based rounds with βt+1\beta_{t+1}βt+1​; Fin K actions with the Fin K order for ties; reason: Lean conventions; same instances
  • encoding: horizon TTT, dimension ddd → T≥1T\ge1T≥1, d≥1d\ge1d≥1; reason: log⁡T\log TlogT is undefined at T=0T=0T=0 (where the regret is 000); the paper works in Rd\mathbb R^dRd
Preamble
import Mathlib
import Definitions.Def_IAFTRL_IsActionSet
import Definitions.Def_IAFTRL_IsIAFTRLRun
import Definitions.Def_LinearBanditProtocol
import Definitions.Def_IAFTRL_actionNorm
import Definitions.Def_IAFTRL_IsUniqueMin
import Definitions.Def_IAFTRL_IsCorrupted
import Definitions.Def_IAFTRL_regretVs
import Definitions.Def_IAFTRL_IsFeasibleAlloc
import Definitions.Def_IAFTRL_allocCost
Formal statement
namespace IAFTRL

open Matrix MeasureTheory

/-- **Proposition 2.1 (regret for every fixed feasible allocation).** Zhao–Tan, *Best-of-Both-Worlds FTRL for Linear Bandits*, arXiv:2611.01299, Proposition 2.1,
p.20: "For linear bandits with finite action sets, IA-FTRL guarantees
`Reg_T = O(d log K + √(dT log K))`, (2.4) in the adversarial regime. Simultaneously, for every
feasible sampling allocation `n` in (1.2), IA-FTRL guarantees
`Reg_T = O(c^n(𝒜, θ) log K · log T + M_n + J_{d,K,Δ_min}√C)`, (2.5) in the corrupted stochastic regime,
where `J_{d,K,Δ_min} = O(√(d log K) Δ_min^{−128/255})`, and `M_n` is a finite constant depending on the
instance `(𝒜, θ)` and the sampling allocation `n`, but independent of `T` and `C`."

There is an absolute constant `c₀ > 0` such that for every dimension `d ≥ 1` and every spanning
finite action set `𝒜` in the unit ball of `ℝ^d`, with `K = |𝒜|`:
1. (2.4) every execution of IA-FTRL for `T ≥ 1` rounds against an adaptive environment has
   `Reg_T(u) ≤ c₀(d log K + √(dT log K))` for every comparator `u ∈ 𝒜`;
2. (2.5) for every `θ` with `‖θ‖_𝒜 ≤ 1` and unique optimal action `a*`, every `Δ₀ ∈ (0, 1]` with
   `Δ₀ ≤ Δ(a)` for all `a ≠ a*`, and every feasible sampling allocation `n` of (1.2), there is a
   constant `M` such that every execution of IA-FTRL for `T ≥ 1` rounds in the corrupted stochastic
   regime with any budget `C ≥ 0` has
   `Reg_T(u) ≤ c₀(c^n(𝒜, θ) log K · log T + √(d log K) Δ₀^{−128/255} √C) + M` for every `u ∈ 𝒜`.

**Formalization Note.** `O(·)` is read with one absolute constant `c₀`, chosen before the instance.
`M` (the paper's `c₀M_n`) is chosen after `(d, K, 𝒜, θ, a*, Δ₀, n)` and before the probability space,
the horizon `T`, the budget `C` and the run, so it is independent of `T` and `C`; `J` is absorbed into
`c₀√(d log K)Δ₀^{−128/255}`. `Δ₀` is any lower bound in `(0, 1]` on the gaps; at `Δ₀ = Δ_min ≤ 1` this
is (2.5). The bound on every `Reg_T(u)` is the bound on `sup_u Reg_T(u)`. -/
theorem proposition_2_1 : ∃ c₀ : ℝ, 0 < c₀ ∧
    ∀ {d K : ℕ}, 1 ≤ d → ∀ (arms : Fin K → Fin d → ℝ), IsActionSet arms →
      (∀ {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) [IsProbabilityMeasure P] (T : ℕ)
          (R : Run d K Ω), 1 ≤ T → IsIAFTRLRun P arms T R →
          ∀ u : Fin K, regretVs P arms T R u ≤
            c₀ * ((d : ℝ) * Real.log K + Real.sqrt ((d : ℝ) * T * Real.log K))) ∧
      (∀ (θ : Fin d → ℝ) (jstar : Fin K) (Δ₀ : ℝ),
        actionNorm arms θ ≤ 1 → IsUniqueMin arms θ jstar → 0 < Δ₀ → Δ₀ ≤ 1 →
        (∀ j, j ≠ jstar → Δ₀ ≤ (arms j - arms jstar) ⬝ᵥ θ) →
        ∀ n : Fin K → ℝ, IsFeasibleAlloc arms θ jstar n →
        ∃ M : ℝ, ∀ {Ω : Type*} [MeasurableSpace Ω] (P : Measure Ω) [IsProbabilityMeasure P]
          (T : ℕ) (C : ℝ) (R : Run d K Ω), 1 ≤ T → 0 ≤ C →
          IsIAFTRLRun P arms T R → IsCorrupted P arms θ C T R →
          ∀ u : Fin K, regretVs P arms T R u ≤
            c₀ * (allocCost arms θ jstar n * Real.log K * Real.log T +
              Real.sqrt ((d : ℝ) * Real.log K) * Δ₀ ^ (-(128 : ℝ) / 255) * Real.sqrt C) + M) := by sorry

end IAFTRL
Source
Zhao–Tan, Best-of-Both-Worlds FTRL for Linear Bandits, arXiv:2611.01299, Section 2.2, Proposition 2.1, p.20, Eqs. (2.4)–(2.5)
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 paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me