Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

Assumption 1 contracts signed measures of total mass zero: ∥μPqa→b∥1≤γb−a∥μ∥1\|\mu P_q^{a\to b}\|_1\le\gamma^{b-a}\|\mu\|_1∥μPqa→b​∥1​≤γb−a∥μ∥1​

Proved
TPG.mixing_contraction

by Wenqian Xing · Oct 12, 2026 · Mathlib 0df444a (Lean v4.33.1)

causal-inferencemarkov-chainnonstationaritypolicy-gradienttreatment-effect

Let the transition matrices PztP^t_zPzt​ of the environment satisfy Assumption 1 on the horizon TTT with a constant γ≥0\gamma\ge0γ≥0: for every t<Tt<Tt<T, every action zzz and every pair of probability vectors f,f′f,f'f,f′ on the finite state space SSS, ∥f′Pzt−fPzt∥TV≤γ ∥f′−f∥TV\|f'P^t_z-fP^t_z\|_{\mathrm{TV}}\le\gamma\,\|f'-f\|_{\mathrm{TV}}∥f′Pzt​−fPzt​∥TV​≤γ∥f′−f∥TV​, with ∥⋅∥TV=12∥⋅∥1\|\cdot\|_{\mathrm{TV}}=\tfrac12\|\cdot\|_1∥⋅∥TV​=21​∥⋅∥1​.

Lemma. Let 0≤qs≤10\le q_s\le10≤qs​≤1 for all sss, let a≤b≤Ta\le b\le Ta≤b≤T, and let μ\muμ be a real row vector on SSS with ∑xμ(x)=0\sum_x\mu(x)=0∑x​μ(x)=0. Then

∥μ PqaaPqa+1a+1⋯Pqb−1b−1∥1≤γ b−a ∥μ∥1,Pθs=θP1s+(1−θ)P0s.\bigl\|\mu\,P^a_{q_a}P^{a+1}_{q_{a+1}}\cdots P^{b-1}_{q_{b-1}}\bigr\|_1\le\gamma^{\,b-a}\,\|\mu\|_1,\qquad P^s_\theta=\theta P^s_1+(1-\theta)P^s_0 .​μPqa​a​Pqa+1​a+1​⋯Pqb−1​b−1​​1​≤γb−a∥μ∥1​,Pθs​=θP1s​+(1−θ)P0s​.

This is the form in which the mixing assumption enters every bias, variance and mixing bound of the source.

Preamble
import Mathlib
import Definitions.Def_TPG_Model
import Definitions.Def_TPG_Estimators
import Definitions.Def_TPG_Markov
import Definitions.Def_TPG_Bridge

open MeasureTheory ProbabilityTheory
open scoped BigOperators ENNReal
Formal statement
namespace TPG
theorem mixing_contraction {S : Type} [Fintype S] [DecidableEq S]
    (E : Env S) (T : ℕ) (γ : ℝ) (hγ : 0 ≤ γ) (hmix : E.Mixing T γ)
    (q : ℕ → ℝ) (hq : ∀ t : ℕ, 0 ≤ q t ∧ q t ≤ 1) (a b : ℕ) (hab : a ≤ b) (hb : b ≤ T)
    (μ : S → ℝ) (hμ : ∑ x, μ x = 0) :
    ∑ x, |Matrix.vecMul μ (((List.Ico a b).map (fun s => E.PMix (q s) s)).prod) x|
      ≤ γ ^ (b - a) * ∑ x, |μ x| := by sorry
end TPG
Source
Johari, Peng, Xing, Estimation of Treatment Effects Under Nonstationarity via the Truncated Policy Gradient Estimator, revised manuscript of October 2026 (revision of arXiv:2506.05308v3, https://arxiv.org/abs/2506.05308); numbering follows the revised manuscript. Auxiliary statement, not a numbered result of the paper: it is eq. (24), p. 38 (Appendix F.1): by Jordan decomposition the contraction of Assumption 1 extends to signed measures of total mass zero and to multi-step kernels.

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