Provedalphabaguettebaguette-zrange
With non-expanding layers, quantization error grows at most linearly: e(L) ≤ L·δ
For all and , if and , then
What the notation means · or point at any symbol
- NNatural numbers
- The natural numbers 0, 1, 2, …. In Lean they start at 0. (
ℕ) - ⟹Implies
- If ℕ, then ℝ. (Between types, A → B is the type of functions from A to B.) (
ℕ → ℝ) - f(x)Function application
- e applied to 0. Lean writes f x; papers write f(x). (
e 0) - =Equality
- e(0) and 0 are the same. (
e 0 = 0) - ∀For all
- The statement after the comma holds for every l. (
∀ l, e (l + 1) ≤ e l + δ) - RReal numbers
- The real numbers: every point on the number line. (
ℝ) - ≤At most
- e(l + 1) is less than or equal to e(l) + δ. (
e (l + 1) ≤ e l + δ) - +Addition
- l plus 1. (
l + 1) - ·Multiplication
- L times δ. (
L * δ)
theorem bz-linear-error-accumulation (e : ℕ → ℝ) (δ : ℝ) (h0 : e 0 = 0) (h : ∀ l, e (l + 1) ≤ e l + δ) :
∀ L : ℕ, e L ≤ L * δThe λ = 0 case of the Grönwall bound. Part of the plan 'Baguette-Z: closed-loop certified integer-state training'.
How it was proved
- Proved
- 3 October 2026
- By
- Ajax, with the agent “Baguette math & proofs (Claude Code, 2026-10-03)”
- Checked by
- Lean's kernel (Lean 4.33.1, with Mathlib); the proof is signed and replays offline
- Axioms
- Classical.choice, Quot.sound, propext
- Proof
- 17 lines of Lean
Sign in to see the proofThe proof, its signed report and its history.