Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma B.7 — instantaneous regret bound

Proved
LinParamBandits.UEGeneral.inst_regret_bound

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

linear-banditp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1regretucb

Consider a run of the UE policy under Assumption 1 and let Qt+1(z)=max⁡v∈Urv′z−Ut+1′zQ_{t+1}(z) = \max_{v \in \mathcal U_r}v'z - U_{t+1}'zQt+1​(z)=maxv∈Ur​​v′z−Ut+1′​z be the instantaneous regret in period t+1t+1t+1 given Z=zZ = zZ=z. For all t≥rt \ge rt≥r and z∈Rrz \in \mathbb R^rz∈Rr,

Pr⁡{Qt+1(z)>2αlog⁡tmin⁡{rlog⁡t,∣Ur∣} ∥Ut+1∥Ct ∣ Z=z}≤1t2.\Pr\Big\{Q_{t+1}(z) > 2\alpha\sqrt{\log t}\sqrt{\min\{r\log t, |\mathcal U_r|\}}\,\|U_{t+1}\|_{C_t} \,\Big|\, Z = z\Big\} \le \frac{1}{t^2}.Pr{Qt+1​(z)>2αlogt​min{rlogt,∣Ur​∣}​∥Ut+1​∥Ct​​​Z=z}≤t21​.

The instantaneous regret is thus, outside an event of probability 1/t21/t^21/t2, at most twice the uncertainty radius of the arm played; this is the basis of the regret decomposition, Lemma B.8.

Formalization Note The statement is about a run of the UE policy (IsUE) under Assumption 1 (Assumption1) on a compact nonempty arm set Ur⊂Rr\mathcal U_r \subset \mathbb R^rUr​⊂Rr, r≥2r \ge 2r≥2, with noise laws given by a Markov kernel ν\nuν (the law of WtuW^u_tWtu​ is ν(u)\nu(u)ν(u) for every ttt). "Pr⁡{⋅∣Z=z}\Pr\{\cdot \mid Z = z\}Pr{⋅∣Z=z}" is the law histMeasure ν z ψ t of the history (U1,X1,…,Ut,Xt)(U_1, X_1, \dots, U_t, X_t)(U1​,X1​,…,Ut​,Xt​) with the parameter fixed to zzz; Ut+1U_{t+1}Ut+1​ is ψ.act t h. CtC_tCt​ is Cmat, the inverse of the design matrix ∑s≤tUsUs′\sum_{s \le t} U_s U_s'∑s≤t​Us​Us′​, which is positive definite on every history that starts with b1,…,brb_1, \dots, b_rb1​,…,br​ (all histories of a UE run, since t≥rt \ge rt≥r). Qt+1(z)Q_{t+1}(z)Qt+1​(z) is instRegret 𝒰 z (ψ.act t h).

Preamble
import Mathlib
import Definitions.Def_LinParamBandits_UEGeneral_Model
import Definitions.Def_LinParamBandits_UEGeneral_UEPolicy
Formal statement
namespace LinParamBandits.UEGeneral

open MeasureTheory ProbabilityTheory

/-- Lemma B.7 (p. 35): instantaneous regret bound. -/
theorem inst_regret_bound {r : ℕ} (hr : 2 ≤ r) {𝒰 : Set (LinParamBandits.LowerBound.Vec r)} (h𝒰c : IsCompact 𝒰) (h𝒰n : 𝒰.Nonempty)
    {ν : Kernel (LinParamBandits.LowerBound.Vec r) ℝ} [IsMarkovKernel ν] {b : Fin r → LinParamBandits.LowerBound.Vec r} {σ₀ ubar lam0 : ℝ}
    (hA : Assumption1 𝒰 ν b σ₀ ubar lam0) {ψ : Policy r} (hψ : IsUE 𝒰 b σ₀ ubar lam0 ψ)
    (t : ℕ) (ht : r ≤ t) (z : LinParamBandits.LowerBound.Vec r) :
    histMeasure ν z ψ t
        {h | 2 * radiusFactor 𝒰 σ₀ ubar lam0 t * wnorm (Cmat (armsOf h)) (ψ.act t h) <
          instRegret 𝒰 z (ψ.act t h)} ≤
      ENNReal.ofReal (1 / (t : ℝ) ^ 2) := by sorry

end LinParamBandits.UEGeneral
Source
Rusmevichientong, Tsitsiklis, Linearly Parameterized Bandits, arXiv:0812.3465v2, Lemma B.7, p. 35; eq. (9), p. 35
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