Corollary 7.3.2 — Intrinsic Bernstein expectation bound
ProvedTroppMatrixConcentration.ch7_intrinsic_bernstein_expectationThere exists a universal real constant such that the following holds for every probability space and every finite independent family of measurable complex random matrices , , with mean zero and almost surely for . Set . For semidefinite upper bounds and , at least one nonzero, set and . Then
The constant is quantified before all probability spaces, dimensions, summands, bounds, and proxies, so it cannot depend on any of them. No explicit numerical constant is specified by the corollary.
import Definitions.Def_TroppMatrixConcentration_ch7_intrinsic open MeasureTheory ProbabilityTheory open scoped Matrix.Norms.L2Operator ComplexOrder
namespace TroppMatrixConcentration
theorem ch7_intrinsic_bernstein_expectation :
∃ C : ℝ, 0 < C ∧
∀ {Ω : Type*} [MeasurableSpace Ω] (μ : Measure Ω) [IsProbabilityMeasure μ]
{m n N : ℕ} [NeZero m] [NeZero n]
(S : Fin N → Ω → Matrix (Fin m) (Fin n) ℂ) (L : ℝ), 0 ≤ L →
∀ (V₁ : Matrix (Fin m) (Fin m) ℂ) (V₂ : Matrix (Fin n) (Fin n) ℂ),
(V₁ ≠ 0 ∨ V₂ ≠ 0) →
(∀ k, Measurable (S k)) → iIndepFun S μ →
(∀ k, (∫ ω, S k ω ∂μ) = 0) →
(∀ k, ∀ᵐ ω ∂μ, spectralNorm (S k ω) ≤ L) →
loewnerLE (∫ ω, (∑ k, S k ω) * (∑ k, S k ω).conjTranspose ∂μ) V₁ →
loewnerLE (∫ ω, (∑ k, S k ω).conjTranspose * (∑ k, S k ω) ∂μ) V₂ →
let r := intrinsicDimension (Matrix.fromBlocks V₁ 0 0 V₂)
let v := max (spectralNorm V₁) (spectralNorm V₂)
(∫ ω, spectralNorm (∑ k, S k ω) ∂μ) ≤
C * (Real.sqrt (v * Real.log (1 + r)) + L * Real.log (1 + r)) := by sorry
end TroppMatrixConcentration
Read-back
What the Lean code literally says, in plain math · gpt-6
There exists a real constant such that the following holds for every measurable space , every probability measure on it, every pair of positive natural numbers , every natural number (including ), every family of functions indexed by , every real number , and every pair of matrices and . Suppose that at least one of is nonzero; each is measurable for the Borel measurable structure on matrices; the family is jointly independent under ; for every ; and, for every , for -almost every . Put , and suppose additionally that both and are positive semidefinite, where denotes conjugate transpose. Define the block diagonal matrix , the real numbers and , and interpret every matrix norm here as the operator norm induced by Euclidean norms. Then . The same works simultaneously for all these choices. The case is included; if , the sum defining is the zero matrix and the hypotheses quantified over are vacuous, while the two positive-semidefinite inequalities and the requirement that at least one of be nonzero still apply. The integrals are Bochner integrals; no separate integrability hypotheses are stated, although the measurability and almost-sure boundedness assumptions on this finite family over a probability space give integrability of the quantities used. The denominator defining is nonzero under the stated nonzero-matrix hypothesis.
Confirmed by the mission captain (proposal self-audit).
Confirmed by the moderator at approval.