Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Lemma B.8 — regret decomposition

Proved
LinParamBandits.UEGeneral.regret_decomposition

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

linear-banditp2o-batch-pfp2bp2o-gran-per-chapterp2o-plan-paperp2o-v1regret

Consider a run of the UE policy under Assumption 1. For all T≥r+1T \ge r+1T≥r+1 and z∈Rrz \in \mathbb R^rz∈Rr,

Regret(z,T,UE)≤2uˉ(r+2)∥z∥+2αr (log⁡T)T  E[∑t=rT−1∥Ut+1∥Ct2  |  Z=z].\mathrm{Regret}(z, T, \mathrm{UE}) \le 2\bar u(r+2)\|z\| + 2\alpha\sqrt r\,(\log T)\sqrt T\;\mathbb E\left[\sqrt{\sum_{t=r}^{T-1}\|U_{t+1}\|^2_{C_t}} \;\middle|\; Z = z\right].Regret(z,T,UE)≤2uˉ(r+2)∥z∥+2αr​(logT)T​E​t=r∑T−1​∥Ut+1​∥Ct​2​​​Z=z​.

The first term covers the rrr initialization periods and the rare periods in which Lemma B.7's event fails; the second reduces the regret to the growth of the weighted arm norms, bounded in Lemmas B.10 and B.11.

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). The expectation on the right is the Bochner integral over histMeasure ν z ψ T of ∑t=rT−1∥Ut+1∥Ct2\sqrt{\sum_{t=r}^{T-1}\|U_{t+1}\|^2_{C_t}}∑t=rT−1​∥Ut+1​∥Ct​2​​, written with potential (armSeq h) t; the integrand is nonnegative and bounded on the support, and a junk value 000 would only make the bound harder.

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.8 (p. 36): regret decomposition. -/
theorem regret_decomposition {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 + 1 ≤ T) (z : LinParamBandits.LowerBound.Vec r) :
    regret ν 𝒰 ψ z T ≤
      2 * ubar * ((r : ℝ) + 2) * ‖z‖ +
        2 * alpha σ₀ ubar lam0 * Real.sqrt r * Real.log T * Real.sqrt T *
          ∫ h, Real.sqrt (∑ t ∈ Finset.Ico r T, potential (armSeq h) t)
            ∂(histMeasure ν z ψ T) := by sorry

end LinParamBandits.UEGeneral
Source
Rusmevichientong, Tsitsiklis, Linearly Parameterized Bandits, arXiv:0812.3465v2, Lemma B.8, p. 36
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